Main Page

Table of Contents

Author Index

Table of Contents

Chairs’ Welcome 
Amal El Fallah Seghrouchni and Gita Sukthankar, AAMAS’20 General Chairs
Bo An and Neil Yorke-Smith, AAMAS’20 Program Chairs


 

(Return to Top)

Keynote Talks

AI for Advancing Scientific Discovery for a Sustainable Future (page 1)
Carla P. Gomes, Cornell University

Automatic Curricula in Deep Multi-Agent Reinforcement Learning (page 2)
Thore Graepel, Google DeepMind

Building Cities from Slime Mould, Agents and Quantum Field Theory (page 3)
Alison Heppenstall, University of Leeds
Nick Malleson, University of Leeds

Unsupervised Reinforcement Learning (page 5)
Sergey Levine, University of California, Berkeley

(Return to Top)

Research Papers

Reconfigurable Interaction for MAS Modelling (page 7)
Yehia Abd Alrahman, University of Gothenburg
Giuseppe Perelli, Sapienza University of Rome
Nir Piterman, University of Gothenburg

Elessar: Ethics in Norm-Aware Agents (page 16)
Nirav Ajmeri, North Carolina State University
Hui Guo, North Carolina State University
Pradeep K. Murukannaiah, Delft University of Technology
Munindar P. Singh, North Carolina State University

Formal Verification of Neural Agents in Non-deterministic Environments (page 25)
Michael E. Akintunde, Imperial College London
Elena Botoeva, Imperial College London
Panagiotis Kouvaros, Imperial College London
Alessio Lomuscio, Imperial College London

Explainable Multi Agent Path Finding (page 34)
Shaull Almagor, Technion - Israel Institute of Technology
Morteza Lahijanian, University of Colorado Boulder

(Return to Top)

Rational vs Byzantine Players in Consensus-based Blockchains (page 43)
Yackolley Amoussou-Guenou, CEA LIST, PC 174 and Sorbonne Université, CNRS, LIP6
Bruno Biais, HEC Paris
Maria Potop-Butucaru, Sorbonne Université, CNRS, LIP6
Sara Tucci-Piergiovanni, CEA LIST, PC 174

Strategic Decision-Making for Power Network Investments with Distributed Renewable Generation (page 52)
Merlinda Andoni, Heriot-Watt University
Valentin Robu, Heriot-Watt University
Wolf-Gerrit Fruh, Heriot-Watt University
David Flynn, School of Engineering & Physical Sciences

A Design-Methodology for Epidemic Dynamics via Time-Varying Hypergraphs (page 61)
Alessia Antelmi, Universitŕ degli Studi di Salerno
Gennaro Cordasco, Universitŕ della Campania "Luigi Vanvitelli"
Carmine Spagnuolo, Universitŕ degli Studi di Salerno
Vittorio Scarano, Universitŕ degli Studi di Salerno

A General Framework for Energy-Efficient Cloud Computing Mechanisms (page 70)
Antonios Antoniadis, Saarland University and Max-Planck-Institut für Informatik
Andrés Cristi, Universidad de Chile
Tim Oosterwijk, Maastricht University
Alkmini Sgouritsa, University of Liverpool

(Return to Top)

Improved Algorithms for Learning Equilibria in Simulation-Based Games (page 79)
Enrique Areyan Viqueira, Brown University
Cyrus Cousins, Brown University
Amy Greenwald, Brown University

Learning an Interpretable Traffic Signal Control Policy (page 88)
James Ault, Texas A&M University
Josiah P. Hanna, University of Edinburgh
Guni Sharon, Texas A&M University

Summer Internship Matching with Funding Constraints (page 97)
Haris Aziz, University of New South Wales & Data61 CSIRO
Anton Baychkov, University of Sydney
Péter Biró, Hungarian Academy of Sciences

HMMs for Anomaly Detection in Autonomous Robots (page 105)
Davide Azzalini, Politecnico di Milano
Alberto Castellini, University of Verona
Matteo Luperto, Universitŕ degli Studi di Milano
Alessandro Farinelli, University of Verona
Francesco Amigoni, Politecnico di Milano

Peer Reviewing in Participatory Guarantee Systems: Modelisation and Algorithmic Aspects (page 114)
Nathanaël Barrot, RIKEN AIP & Kyushu University
Sylvaine Lemeilleur, CIRAD
Nicolas Paget, CIRAD
Abdallah Saffidine, The University of New South Wales

Learning to Optimize Autonomy in Competence-Aware Systems (page 123)
Connor Basich, University of Massachusetts, Amherst
Justin Svegliato, University of Massachusetts, Amherst
Kyle Hollins Wray, Alliance Innovation Lab Silicon Valley
Stefan Witwicki, Alliance Innovation Lab Silicon Valley
Joydeep Biswas, The University of Texas at Austin
Shlomo Zilberstein, University of Massachusetts, Amherst

(Return to Top)

Manipulation of Opinion Polls to Influence Iterative Elections (page 132)
Dorothea Baumeister, Heinrich-Heine-Universität Düsseldorf
Ann-Kathrin Selker, Heinrich-Heine-Universität Düsseldorf
Anaëlle Wilczynski, Technical University of Munich

Optimising Game Tactics for Football (page 141)
Ryan Beal, University of Southampton
Georgios Chalkiadakis, Technical University of Crete
Timothy J. Norman, University of Southampton
Sarvapali D. Ramchurn, University of Southampton

Candidate Selections with Proportional Fairness Constraints (page 150)
Xiaohui Bei, Nanyang Technological University
Shengxin Liu, Nanyang Technological University
Chung Keung Poon, The Hang Seng University of Hong Kong
Hongao Wang, Nanyang Technological University

Multi-Agent Path Finding in Configurable Environments (page 159)
Matteo Bellusci, Politecnico di Milano
Nicola Basilico, Universitŕ degli Studi di Milano
Francesco Amigoni, Politecnico di Milano

Automated Justification of Collective Decisions via Constraint Solving (page 168)
Arthur Boixel, University of Amsterdam
Ulle Endriss, University of Amsterdam

Input Addition and Deletion in Reinforcement: Towards Learning with Structural Changes (page 177)
Iago Bonnici, LIRMM, Université de Montpellier, CNRS
Abdelkader Gouaďch, LIRMM, Université de Montpellier, CNRS
Fabien Michel, LIRMM, Université de Montpellier, CNRS

(Return to Top)

Majority-Strategyproofness in Judgment Aggregation (page 186)
Sirin Botan, University of Amsterdam
Ulle Endriss, University of Amsterdam

Finding and Recognizing Popular Coalition Structures (page 195)
Felix Brandt, Technische Universität München
Martin Bullinger, Technische Universität München

Fair Allocation of Resources with Uncertain Availability (page 204)
Jan Buermann, University of Southampton
Enrico H. Gerding, University of Southampton
Baharak Rastegari, University of Southampton

Pareto-Optimality in Cardinal Hedonic Games (page 213)
Martin Bullinger, Technische Universität München

Task Allocation Strategy for Heterogeneous Robot Teams in Offshore Missions (page 222)
Yaniel Carreno, Heriot-Watt University & University of Edinburgh
Čric Pairet, Heriot-Watt University & University of Edinburgh
Yvan Petillot, Heriot-Watt University
Ronald P. A. Petrick, Heriot-Watt University

Weighted Envy-Freeness in Indivisible Item Allocation (page 231)
Mithun Chakraborty, University of Michigan - Ann Arbor
Ayumi Igarashi, University of Tokyo
Warut Suksompong, University of Oxford
Yair Zick, National University of Singapore

(Return to Top)

Schelling Models with Localized Social Influence: A Game-Theoretic Framework (page 240)
Hau Chan, University of Nebraska-Lincoln
Mohammad T. Irfan, Bowdoin College
Cuong Viet Than, University of Nebraska-Lincoln

RMB-DPOP: Refining MB-DPOP by Reducing Redundant Inference (page 249)
Ziyu Chen, Chongqing University
Wenxin Zhang, Chongqing University
Yanchen Deng, Chongqing University
Dingding Chen, Chongqing University
Qiang Li, Chongqing University

Refinement for Multiagent Protocols (page 258)
Samuel H. Christie, V, North Carolina State University
Amit K. Chopra, Lancaster University
Munindar P. Singh, North Carolina State University

Policy Synthesis for Factored MDPs with Graph Temporal Logic Specifications (page 267)
Murat Cubuktepe, The University of Texas at Austin
Zhe Xu, The University of Texas at Austin
Ufuk Topcu, The University of Texas at Austin

Leader Election and Compaction for Asynchronous Silent Programmable Matter (page 276)
Gianlorenzo D'Angelo, Gran Sasso Science Institute
Mattia D'Emidio, University of L'Aquila
Shantanu Das, Aix-Marseille University
Alfredo Navarra, University of Perugia
Giuseppe Prencipe, University of Pisa

Intention-Aware Multiagent Scheduling (page 285)
Michael Dann, RMIT University
John Thangarajah, RMIT University
Yuan Yao, Zhejiang University of Technology
Brian Logan, University of Nottingham

(Return to Top)

Goal Formation through Interaction in the Situation Calculus: A Formal Account Grounded in Behavioral Science (page 294)
Giuseppe De Giacomo, Universitŕ degli Studi di Roma
Yves Lespérance, York University

Risk-Aware Conditional Replanning for Globally Constrained Multi-Agent Sequential Decision Making (page 303)
Frits de Nijs, Monash University
Peter J. Stuckey, Monash University

Testing Axioms Against Human Reward Divisions in Cooperative Games (page 312)
Greg d'Eon, University of British Columbia
Kate Larson, University of Waterloo

Manipulating Node Similarity Measures in Networks (page 321)
Palash Dey, Indian Institute of Technology
Sourav Medya, Northwestern University

Gaussian Processes as Multiagent Reward Models (page 330)
Gaurav Dixit, Oregon State University
Stéphane Airiau, LAMSADE, CNRS, Université Paris-Dauphine, Université PSL
Kagan Tumer, Oregon State University

Alternative Function Approximation Parameterizations for Solving Games: An Analysis of f-Regression Counterfactual Regret Minimization (page 339)
Ryan D'Orazio, University of Alberta
Dustin Morrill, University of Alberta
James R. Wright, University of Alberta
Michael Bowling, University of Alberta

(Return to Top)

Dueling Bandits: From Two-dueling to Multi-dueling (page 348)
Yihan Du, Tsinghua University
Siwei Wang, Tsinghua University
Longbo Huang, Tsinghua University

Private and Byzantine-Proof Cooperative Decision-Making (page 357)
Abhimanyu Dubey, Massachusetts Institute of Technology
Alex Pentland, Massachusetts Institute of Technology

Algorithms for Swap and Shift Bribery in Structured Elections (page 366)
Edith Elkind, University of Oxford
Piotr Faliszewski, AGH University
Sushmita Gupta, National Institute of Science Education and Research
Sanjukta Roy, The Institute of Mathematical Sciences, HBNI

Adaptive Autonomy in Wireless Sensor Networks (page 375)
Mirgita Frasheri, Mälardalen University
José Cano-Garcia, University of Malaga
Eva González-Parada, University of Malaga
Baran Çürüklü, Mälardalen University
Mikael Ekström, Mälardalen University
Alessandro V. Papadopoulos, Mälardalen University
Cristina Urdiales, University of Malaga

Equitable Allocations of Indivisible Chores (page 384)
Rupert Freeman, Microsoft Research
Sujoy Sikdar, University of Washington in St. Louis
Rohit Vaish, Rensselaer Polytechnic Institute
Lirong Xia, Rensselaer Polytechnic Institute

Threshold Task Games: Theory, Platform and Experiments (page 393)
Kobi Gal, Ben-Gurion University of the Negev & University of Edinburgh
Ta Duy Nguyen, National University of Singapore
Quang Nhat Tran, National University of Singapore
Yair Zick, National University of Singapore

(Return to Top)

Mechanism Design for Defense Coordination in Security Games (page 402)
Jiarui Gan, University of Oxford
Edith Elkind, University of Oxford
Sarit Kraus, Bar-Ilan University
Michael Wooldridge, University of Oxford

Multi Type Mean Field Reinforcement Learning (page 411)
Sriram Ganapathi Subramanian, University of Waterloo
Pascal Poupart, Borealis AI
Matthew E. Taylor, Borealis AI
Nidhi Hegde, Borealis AI

Computing Competitive Equilibria with Mixed Manna (page 420)
Jugal Garg, University of Illinois at Urbana-Champaign
Peter McGlaughlin, University of Illinois at Urbana-Champaign

Toward Genuine Robot Teammates: Improving Human-Robot Team Performance Using Robot Shared Mental Models (page 429)
Felix Gervits, Tufts University
Dean Thurston, Tufts University
Ravenna Thielstrom, Tufts University
Terry Fong, NASA Ames Research Center
Quinn Pham, Tufts University
Matthias Scheutz, Tufts University

Improving Performance in Reinforcement Learning by Breaking Generalization in Neural Networks (page 438)
Sina Ghiassian, University of Alberta; Alberta Machine Intelligence Institute
Banafsheh Rafiee, University of Alberta; Alberta Machine Intelligence Institute
Yat Long Lo, University of Alberta; Alberta Machine Intelligence Institute
Adam White, University of Alberta; Alberta Machine Intelligence Institute

Towards Deployment of Robust Cooperative AI Agents: An Algorithmic Framework for Learning Adaptive Policies (page 447)
Ahana Ghosh, MPI-SWS
Sebastian Tschiatschek, University of Vienna
Hamed Mahdavi, MPI-SWS
Adish Singla, MPI-SWS

(Return to Top)

A Bridge between Polynomial Optimization and Games with Imperfect Recall (page 456)
Hugo Gimbert, CNRS, LaBRI , Université de Bordeaux
Soumyajit Paul, LaBRI , Université de Bordeaux
B. Srivathsan, Chennai Mathematical Institute

Integrating Behavior Cloning and Reinforcement Learning for Improved Performance in Dense and Sparse Reward Environments (page 465)
Vinicius G. Goecks, Texas A&M University and US Army Research Laboratory
Gregory M. Gremillion, US Army Research Laboratory
Vernon J. Lawhern, US Army Research Laboratory
John Valasek, Texas A&M University
Nicholas R. Waytowich, US Army Research Laboratory & Columbia University

Demystifying Emergent Intelligence and Its Effect on Performance In Large Robot Swarms (page 474)
John Harwell, University of Minnesota
London Lowmanstone, Harvard University
Maria Gini, University of Minnesota

Cautious Reinforcement Learning with Logical Constraints (page 483)
Mohammadhosein Hasanbeig, University of Oxford
Alessandro Abate, University of Oxford
Daniel Kroening, University of Oxford

Neural Replicator Dynamics: Multiagent Learning via Hedging Policy Gradients (page 492)
Daniel Hennes, DeepMind
Dustin Morrill, University of Alberta
Shayegan Omidshafiei, DeepMind
Rémi Munos, DeepMind
Julien Perolat, DeepMind
Marc Lanctot, DeepMind
Audrunas Gruslys, DeepMind
Jean-Baptiste Lespiau, DeepMind
Paavo Parmas, Okinawa Institute of Science and Technology
Edgar Dučńez-Guzmán, DeepMind
Karl Tuyls, DeepMind

New Algorithms for Continuous Distributed Constraint Optimization Problems (page 502)
Khoi D. Hoang, Washington University in St. Louis
William Yeoh, Washington University in St. Louis
Makoto Yokoo, Kyushu University
Zinovi Rabinovich, Nanyang Technological University

(Return to Top)

The Effect of Strategic Noise in Linear Regression (page 511)
Safwan Hossain, University of Toronto
Nisarg Shah, University of Toronto

Inducing Cooperation through Reward Reshaping based on Peer Evaluations in Deep Multi-Agent Reinforcement Learning (page 520)
David Earl Hostallero, McGill University
Daewoo Kim, Korea Advanced Institute of Science and Technology
Sangwoo Moon, Korea Advanced Institute of Science and Technology
Kyunghwan Son, Korea Advanced Institute of Science and Technology
Wan Ju Kang, Korea Advanced Institute of Science and Technology
Yung Yi, Korea Advanced Institute of Science and Technology

Green Security Game with Community Engagement (page 529)
Taoan Huang, University of Southern California
Weiran Shen, Carnegie Mellon University
David Zeng, Carnegie Mellon University
Tianyu Gu, Carnegie Mellon University
Rohit Singh, World Wide Fund for Nature
Fei Fang, Carnegie Mellon University

Learning to Resolve Alliance Dilemmas in Many-Player Zero-Sum Games (page 538)
Edward Hughes, DeepMind
Thomas W. Anthony, DeepMind
Tom Eccles, DeepMind
Joel Z. Leibo, DeepMind
David Balduzzi, DeepMind
Yoram Bachrach, DeepMind

CopyCAT: Taking Control of Neural Policies with Constant Attacks (page 548)
Léonard Hussenot, Google Research, INRIA SequeL & Université de Lille
Matthieu Geist, Google Research
Olivier Pietquin, Google Research

Snooping Attacks on Deep Reinforcement Learning (page 557)
Matthew Inkawhich, Duke University
Yiran Chen, Duke University
Hai Li, Duke University

(Return to Top)

It's Not Whom You Know, It's What You, or Your Friends, Can Do: Coalitional Frameworks for Network Centralities (page 566)
Gabriel Istrate, West University of Timisoara & The e-Austria Research Institute
Cosmin Bonchiş, West University of Timisoara & The e-Austria Research Institute
Claudiu Gatină, West University of Timisoara

Influence Maximization in Unknown Social Networks: Learning Policies for Effective Graph Sampling (page 575)
Harshavardhan Kamarthi, Indian Institute of Technology Madras
Priyesh Vijayan, McGill University and Mila
Bryan Wilder, Harvard University
Balaraman Ravindran, Indian Institute of Technology Madras
Milind Tambe, Harvard University

On Stable Matchings with Pairwise Preferences and Matroid Constraints (page 584)
Naoyuki Kamiyama, Kyushu University & JST PRESTO

Combining No-regret and Q-learning (page 593)
Ian A. Kash, University of Illinois at Chicago
Michael Sullins, University of Illinois at Chicago
Katja Hofmann, Microsoft Research

Approximately Stable Matchings with General Constraints (page 602)
Yasushi Kawase, Tokyo Institute of Technology & RIKEN AIP
Atsushi Iwasaki, University of Electro-Communications & RIKEN AIP

Inducing Equilibria in Networked Public Goods Games through Network Structure Modification (page 611)
David Kempe, University of Southern California
Sixie Yu, Washington University in St. Louis
Yevgeniy Vorobeychik, Washington University in St. Louis

(Return to Top)

Learning Hierarchical Teaching Policies for Cooperative Agents (page 620)
Dong-Ki Kim, Massachusetts Institute of Technology & MIT-IBM Watson AI Lab
Miao Liu, IBM Research, MIT-IBM Watson AI Lab
Shayegan Omidshafiei, Massachusetts Institute of Technology & MIT-IBM Watson AI Lab
Sebastian Lopez-Cot, Massachusetts Institute of Technology & MIT-IBM Watson AI Lab
Matthew Riemer, IBM Research, MIT-IBM Watson AI Lab
Golnaz Habibi, Massachusetts Institute of Technology & MIT-IBM Watson AI Lab
Gerald Tesauro, IBM Research, MIT-IBM Watson AI Lab
Sami Mourad, IBM Research, MIT-IBM Watson AI Lab
Murray Campbell, IBM Research, MIT-IBM Watson AI Lab
Jonathan P. How, Massachusetts Institute of Technology & MIT-IBM Watson AI Lab

Adversarial Patrolling with Drones (page 629)
David Klaška, Masaryk University
Antonín Kučera, Masaryk University
Vojtěch Řehák, Masaryk University

Incentivising Participation in Liquid Democracy with Breadth-First Delegation (page 638)
Grammateia Kotsialou, King's College London
Luke Riley, King's College London & Quant Network

Strategic Manipulation with Incomplete Preferences: Possibilities and Impossibilities for Positional Scoring Rules (page 645)
Justin Kruger, Université Paris-Dauphine
Zoi Terzopoulou, Institute for Logic, Language and Computation

Increasing Evacuation during Disaster Events (page 654)
Chris J. Kuhlman, University of Virginia
Achla Marathe, University of Virginia
Anil Vullikanti, University of Virginia
Nafisa Halim, Boston University
Pallab Mozumder, Florida International University

Convexity of Hypergraph Matching Game (page 663)
Soh Kumabe, The University of Tokyo
Takanori Maehara, RIKEN AIP

(Return to Top)

Optimal Swarm Strategy for Dynamic Target Search and Tracking (page 672)
Hian Lee Kwa, Singapore University of Technology and Design & Thales Solutions Asia
Jabez Leong Kit, Singapore University of Technology and Design
Roland Bouffanais, Singapore University of Technology and Design

On the Model-Checking of Branching-time Temporal Logic with BDI Modalities (page 681)
Salvatore La Torre, Universitŕ degli Studi di Salerno
Gennaro Parlato, Universitŕ degli Studi del Molise

Hindsight Planner (page 690)
Yaqing Lai, Tsinghua University
Wufan Wang, Tsinghua University
Yunjie Yang, Tsinghua University
Jihong Zhu, Tsinghua University
Minchi Kuang, Tsinghua University

A Deliberate BIAT Logic for Modeling Manipulations (page 699)
Christopher Leturc, Normandie University, UNICAEN, ENSICAEN, CNRS, GREYC
Grégory Bonnet, Normandie University, UNICAEN, ENSICAEN, CNRS, GREYC

Fair Resource Sharing and Dorm Assignment (page 708)
Bo Li, University of Oxford
Yingkai Li, Northwestern University

Spatial-Temporal Moving Target Defense: A Markov Stackelberg Game Model (page 717)
Henger Li, Tulane University
Wen Shen, Tulane University
Zizhan Zheng, Tulane University

(Return to Top)

Moving Agents in Formation in Congested Environments (page 726)
Jiaoyang Li, University of Southern California
Kexuan Sun, University of Southern California
Hang Ma, Simon Fraser University
Ariel Felner, Ben-Gurion University of the Negev
T. K. Satish Kumar, University of Southern California
Sven Koenig, University of Southern California

On Emergent Communication in Competitive Multi-Agent Teams (page 735)
Paul Pu Liang, Carnegie Mellon University
Jeffrey Chen, Carnegie Mellon University
Ruslan Salakhutdinov, Carnegie Mellon University
Louis-Philippe Morency, Carnegie Mellon University
Satwik Kottur, Carnegie Mellon University

A Story of Two Streams: Reinforcement Learning Models from Human Behavior and Neuropsychiatry (page 744)
Baihan Lin, Columbia University
Guillermo Cecchi, IBM Research
Djallel Bouneffouf, IBM Research
Jenna Reinen, IBM Research
Irina Rish, Mila, Université de Montréal

Off-Policy Deep Reinforcement Learning with Analogous Disentangled Exploration (page 753)
Anji Liu, University of California, Los Angeles
Yitao Liang, University of California, Los Angeles
Guy Van den Broeck, University of California, Los Angeles

Parameterised Verification of Strategic Properties in Probabilistic Multi-Agent Systems (page 762)
Alessio Lomuscio, Imperial College London
Edoardo Pirovano, Imperial College London

Competitive Ratios for Online Multi-capacity Ridesharing (page 771)
Meghna Lowalekar, Singapore Management University
Pradeep Varakantham, Singapore Management University
Patrick Jaillet, Massachusetts Institute of Technology

(Return to Top)

A Budget-Limited Mechanism for Category-Aware Crowdsourcing Systems (page 780)
Yuan Luo, Imperial College London
Nicholas R. Jennings, Imperial College London

Gifting in Multi-Agent Reinforcement Learning (page 789)
Andrei Lupu, Mila, McGill University
Doina Precup, Mila, McGill University

Likelihood Quantile Networks for Coordinating Multi-Agent Reinforcement Learning (page 798)
Xueguang Lyu, Northeastern University
Christopher Amato, Northeastern University

Penalty Bidding Mechanisms for Allocating Resources and Overcoming Present-Bias (page 807)
Hongyao Ma, Harvard University
Reshef Meir, Technion - Israel Institute of Technology
David C. Parkes, Harvard University
Elena Wu-Yan, Facebook, Inc.

Feudal Multi-Agent Deep Reinforcement Learning for Traffic Signal Control (page 816)
Jinming Ma, University of Science and Technology of China
Feng Wu, University of Science and Technology of China

AED: An Anytime Evolutionary DCOP Algorithm (page 825)
Saaduddin Mahmud, University of Dhaka
Moumita Choudhury, University of Dhaka
Md. Mosaddek Khan, University of Dhaka
Long Tran-Thanh, University of Southampton
Nicholas R. Jennings, Imperial College London

(Return to Top)

Learning Probably Approximately Correct Maximin Strategies in Simulation-Based Games with Infinite Strategy Spaces (page 834)
Alberto Marchesi, Politecnico di Milano
Francesco Trovň, Politecnico di Milano
Nicola Gatti, Politecnico di Milano

(Return to Top)

Optimal Temporal Plan Merging (page 851)
Gilberto Marcon dos Santos, Oregon State University
Julie A. Adams, Oregon State University

Policy-Gradient Algorithms Have No Guarantees of Convergence in Linear Quadratic Games (page 860)
Eric Mazumdar, University of California, Berkeley
Lillian J. Ratliff, University of Washington
Michael I. Jordan, University of California, Berkeley
S. Shankar Sastry, University of California, Berkeley

Social Diversity and Social Preferences in Mixed-Motive Reinforcement Learning (page 869)
Kevin R. McKee, DeepMind
Ian Gemp, DeepMind
Brian McWilliams, DeepMind
Edgar A. Dučñez-Guzmán, DeepMind
Edward Hughes, DeepMind
Joel Z. Leibo, DeepMind

Trajectory-User Linking with Attentive Recurrent Network (page 878)
Congcong Miao, Tsinghua University & Beijing National Research Center for Information Science and Technology
Jilong Wang, Tsinghua University & Beijing National Research Center for Information Science and Technology
Heng Yu, Tsinghua University & Beijing National Research Center for Information Science and Technology
Weichen Zhang, Tsinghua University & Beijing National Research Center for Information Science and Technology
Yinyao Qi, Tsinghua University & Beijing National Research Center for Information Science and Technology

Approximate Nash Equilibria of Imitation Games: Algorithms and Complexity (page 887)
Aniket Murhekar, University of Illinois at Urbana-Champaign
Ruta Mehta, University of Illinois at Urbana-Champaign

(Return to Top)

Massive Cross-Platform Simulations of Online Social Networks (page 895)
Goran Murić, USC Information Sciences Institute
Alexey Tregubov, USC Information Sciences Institute
Jim Blythe, USC Information Sciences Institute
Andrés Abeliuk, USC Information Sciences Institute
Divya Choudhary, USC Information Sciences Institute
, USC Information Sciences Institute
Kristina Lerman, USC Information Sciences Institute
Emilio Ferrara, USC Information Sciences Institute

Duty to Warn in Strategic Games (page 904)
Pavel Naumov, Tulane University
Jia Tao, Lafayette College

Generalized Optimistic Q-Learning with Provable Efficiency (page 913)
Grigory Neustroev, Delft University of Technology
Mathijs M. de Weerdt, Delft University of Technology

The Complexity of Cloning Candidates in Multiwinner Elections (page 922)
Marc Neveling, Heinrich-Heine-Universität Düsseldorf
Jörg Rothe, Heinrich-Heine-Universität Düsseldorf

DCRAC: Deep Conditioned Recurrent Actor-Critic for Multi-Objective Partially Observable Environments (page 931)
Xiaodong Nian, University of Washington
Athirai A. Irissappane, University of Washington
Diederik Roijers, HU University of Applied Sciences

Is the Policy Gradient a Gradient? (page 939)
Chris Nota, University of Massachusetts, Amherst
Philip S. Thomas, University of Massachusetts, Amherst

Driving Exploration by Maximum Distribution in Gaussian Process Bandits (page 948)
Alessandro Nuara, Politecnico di Milano
Francesco Trovň, Politecnico di Milano
Dominic Crippa, Politecnico di Milano
Nicola Gatti, Politecnico di Milano
Marcello Restelli, Politecnico di Milano

(Return to Top)

Multiwinner Candidacy Games (page 957)
Svetlana Obraztsova, Nanyang Technological University
Maria Polukarov, King's College
Edith Elkind, University of Oxford
Marek Grzesiuk, King's College London

Towards a Computational Framework for Automating Substance Use Counseling with Virtual Agents (page 966)
Stefan Olafsson, Northeastern University
Byron Wallace, Northeastern University
Timothy Bickmore, Northeastern University

Analyzing Reinforcement Learning Benchmarks with Random Weight Guessing (page 975)
Declan Oller, Independent Researcher
Tobias Glasmachers, Ruhr-University Bochum
Giuseppe Cuccu, University of Fribourg

Non-Uniform Policies for Multi-Robot Asymmetric Perimeter Patrol in Adversarial Domains (page 983)
Yaniv Oshrat, Bar-Ilan University
Noa Agmon, Bar-Ilan University
Sarit Kraus, Bar-Ilan University

Who and When to Screen: Multi-Round Active Screening for Network Recurrent Infectious Diseases Under Uncertainty (page 992)
Han-Ching Ou, Harvard University
Arunesh Sinha, Singapore Management University
Sze-Chuan Suen, University of Southern California
Andrew Perrault, Harvard University
Alpan Raval, Wadhwani AI
Milind Tambe, Harvard University

Multi-Path Policy Optimization (page 1001)
Ling Pan, Tsinghua University
Qingpeng Cai, Alibaba Group
Longbo Huang, Tsinghua University

(Return to Top)

Navigating the Combinatorics of Virtual Agent Design Space to Maximize Persuasion (page 1010)
Dhaval Parmar, Northeastern University
Stefán Ólafsson, Northeastern University
Dina Utami, Northeastern University
Prasanth Murali, Northeastern University
Timothy Bickmore, Northeastern University

Real-time Learning and Planning in Environments with Swarms: A Hierarchical and a Parameter-based Simulation Approach (page 1019)
Lukasz Pelcner, Lancaster University
Shaling Li, University of Portsmouth
Matheus Aparecido do Carmo Alves, University of Săo Paulo
Leandro Soriano Marcolino, Lancaster University
Alex Collins, Lancaster University

GAPCoD: A Generic Assembly Planner by Constrained Disassembly (page 1028)
Florian Pescher, FEMTO-ST Institute, UBFC, CNRS
Nils Napp, Cornell University
Benoît Piranda, FEMTO-ST Institute, UBFC, CNRS
Julien Bourgeois, FEMTO-ST Institute, UBFC, CNRS

Inference-Based Strategy Alignment for General-Sum Differential Games (page 1037)
Lasse Peters, Hamburg University of Technology
David Fridovich-Keil, University of California, Berkeley
Claire J. Tomlin, University of California, Berkeley
Zachary N. Sunberg, University of Colorado, Boulder

On Algorithmic Decision Procedures in Emergency Response Systems in Smart and Connected Communities (page 1046)
Geoffrey Pettet, Vanderbilt University
Ayan Mukhopadhyay, Stanford University
Mykel Kochenderfer, Stanford University
Yevgeniy Vorobeychik, Washington University
Abhishek Dubey, Vanderbilt University

Learning and Testing Resilience in Cooperative Multi-Agent Systems (page 1055)
Thomy Phan, Ludwig Maximilian University of Munich
Thomas Gabor, Ludwig Maximilian University of Munich
Andreas Sedlmeier, Ludwig Maximilian University of Munich
Fabian Ritz, Ludwig Maximilian University of Munich
Bernhard Kempter, Siemens AG
Cornel Klein, Siemens AG
Horst Sauer, Siemens AG
Reiner Schmid, Siemens AG
Jan Wieghardt, Siemens AG
Marc Zeller, Siemens AG
Claudia Linnhoff-Popien, Ludwig Maximilian University of Munich

(Return to Top)

Objective Social Choice: Using Auxiliary Information to Improve Voting Outcomes (page 1064)
Silviu Pitis, University of Toronto
Michael R. Zhang, University of Toronto

Goal Recognition Using Off-The-Shelf Process Mining Techniques (page 1072)
Artem Polyvyanyy, The University of Melbourne
Zihang Su, The University of Melbourne
Nir Lipovetzky, The University of Melbourne
Sebastian Sardina, RMIT University

Extending Narrative Planning Domains with Linguistic Resources (page 1081)
Julie Porteous, RMIT University
Joăo F. Ferreira, INESC-ID & Instituto Superior Tecnico, Universidade de Lisboa
Alan Lindsay, University of Huddersfield
Marc Cavazza, University of Greenwich

Yesterday's Reward is Today's Punishment: Contrast Effects in Human Feedback to Reinforcement Learning Agents (page 1090)
Divya Ramesh, University of Michigan - Ann Arbor
Anthony Z. Liu, University of Michigan - Ann Arbor
Andres J. Echeverria, University of Michigan - Ann Arbor
Jean Y. Song, University of Michigan - Ann Arbor
Nicholas R. Waytowich, US Army Research Laboratory
Walter S. Lasecki, University of Michigan - Ann Arbor

Toll-Based Learning for Minimising Congestion under Heterogeneous Preferences (page 1098)
Gabriel de O. Ramos, Universidade do Vale do Rio dos Sinos
Roxana Rădulescu, Vrije Universiteit Brussel
Ann Nowé, Vrije Universiteit Brussel
Anderson R. Tavares, Universidade Federal do Rio Grande do Sul

Culture-Based Explainable Human-Agent Deconfliction (page 1107)
Alex Raymond, University of Cambridge
Hatice Gunes, University of Cambridge
Amanda Prorok, University of Cambridge

(Return to Top)

Automated Configuration of Negotiation Strategies (page 1116)
Bram M. Renting, Delft University of Technology
Holger H. Hoos, Leiden University
Catholijn M. Jonker, Delft University of Technology & Leiden University

Capacity, Bandwidth, and Compositionality in Emergent Language Learning (page 1125)
Cinjon Resnick, New York University
Abhinav Gupta, MILA
Jakob Foerster, Facebook AI Research
Andrew M. Dai, Google AI
Kyunghyun Cho, New York University & Facebook AI Research

Employing Models of Human Social Motor Behavior for Artificial Agent Trainers (page 1134)
Lillian M. Rigoli, Macquarie University
Patrick Nalepka, Macquarie University
Hannah Douglas, Macquarie University
Rachel W. Kallen, Macquarie University
Simon Hosking, Defence Science and Technology Group
Christopher Best, Defence Science and Technology Group
Elliot Saltzman, Boston University, MA & Haskins Laboratories
Michael J. Richardson, Macquarie University

Multi-level Fitness Critics for Cooperative Coevolution (page 1143)
Golden Rockefeller, Oregon State University
Shauharda Khadka, Intel Corporation
Kagan Tumer, Oregon State University

A Structural Solution to Sequential Moral Dilemmas (page 1152)
Manel Rodriguez-Soto, Artificial Intelligence Research Institute (IIIA-CSIC)
Maite Lopez-Sanchez, Universitat de Barcelona (UB)
Juan A. Rodriguez-Aguilar, Artificial Intelligence Research Institute (IIIA-CSIC)

Human-Centered Decision Support for Agenda Scheduling (page 1161)
Stephanie Rosenthal, Carnegie Mellon University
Laura M. Hiatt, Naval Research Laboratory

(Return to Top)

Viral vs. Effective: Utility Based Influence Maximization (page 1169)
Yael Sabato, Ariel University
Amos Azaria, Ariel University
Noam Hazon, Ariel University

Multirobot Coverage of Modular Environments (page 1178)
Mirko Salaris, Politecnico di Milano
Alessandro Riva, Politecnico di Milano
Francesco Amigoni, Politecnico di Milano

Designing Effective and Practical Interventions to Contain Epidemics (page 1187)
Prathyush Sambaturu, University of Virginia
Bijaya Adhikari, Virginia Polytechnic Institute and State University
B. Aditya Prakash, Georgia Institute of Technology
Srinivasan Venkatramanan, University of Virginia
Anil Vullikanti, University of Virginia

MGpi: A Computational Model of Multiagent Group Perception and Interaction (page 1196)
Navyata Sanghvi, Carnegie Mellon University
Ryo Yonetani, Carnegie Mellon University
Kris Kitani, Carnegie Mellon University

Bayesian Active Malware Analysis (page 1206)
Riccardo Sartea, University of Verona
Georgios Chalkiadakis, Technical University of Crete
Alessandro Farinelli, University of Verona
Matteo Murari, University of Verona

Maximizing Information Gain in Partially Observable Environments via Prediction Rewards (page 1215)
Yash Satsangi, University of Alberta
Sungsu Lim, University of Alberta
Shimon Whiteson, University of Oxford
Frans A. Oliehoek, Technical University Delft
Martha White, University of Alberta

(Return to Top)

Limitations of Greed: Influence Maximization in Undirected Networks Re-visited (page 1224)
Grant Schoenebeck, University of Michigan - Ann Arbor
Biaoshuai Tao, University of Michigan - Ann Arbor
Fang-Yi Yu, University of Michigan - Ann Arbor

A Qualitative Approach to Composing Value-Aligned Norm Systems (page 1233)
Marc Serramia, Artificial Intelligence Research Institute (IIIA-CSIC)
Maite Lopez-Sanchez, University of Barcelona
Juan A. Rodriguez-Aguilar, Artificial Intelligence Research Institute (IIIA-CSIC)

Learning to Design Coupons in Online Advertising Markets (page 1242)
Weiran Shen, Tsinghua University
Pingzhong Tang, Tsinghua University
Xun Wang, Tsinghua University
Yadong Xu, Tsinghua University
Xiwang Yang, ByteDance

Epistemic Plan Recognition (page 1251)
Maayan Shvo, University of Toronto
Toryn Q. Klassen, University of Toronto
Shirin Sohrabi, IBM Research
Sheila A. McIlraith, University of Toronto

Playing Games in the Dark: An Approach for Cross-Modality Transfer in Reinforcement Learning (page 1260)
Rui Silva, Universidade de Lisboa & Carnegie Mellon University
Miguel Vasco, Universidade de Lisboa
Francisco S. Melo, Universidade de Lisboa
Ana Paiva, Universidade de Lisboa
Manuela Veloso, Carnegie Mellon University

Safe Policy Improvement with an Estimated Baseline Policy (page 1269)
Thiago D. Simăo, Delft University of Technology
Romain Laroche, Microsoft Research
Rémi Tachet des Combes, Microsoft Research

(Return to Top)

Hierarchical Multiagent Reinforcement Learning for Maritime Traffic Management (page 1278)
Arambam James Singh, Singapore Management University
Akshat Kumar, Singapore Management University
Hoong Chuin Lau, Singapore Management University

Signed Graph Games: Coalitional Games with Friends, Enemies and Allies (page 1287)
Oskar Skibski, University of Warsaw
Takamasa Suzuki, Gifu University
Tomasz Grabowski, University of Warsaw
Tomasz Michalak, University of Warsaw
Makoto Yokoo, Kyushu University

Strategyproof Reinforcement Learning for Online Resource Allocation (page 1296)
Sebastian Stein, University of Southampton
Mateusz Ochal, University of Edinburgh
Ioana-Adriana Moisoiu, University of Southampton
Enrico Gerding, University of Southampton
Raghu Ganti, IBM Research
Ting He, Penn State University
Tom La Porta, Penn State University

Minimizing Margin of Victory for Fair Political and Educational Districting (page 1305)
Ana-Andreea Stoica, Columbia University
Abhijnan Chakraborty, Max Planck Institute for Software Systems
Palash Dey, Indian Institute of Technology
Krishna P. Gummadi, Max Planck Institute for Software Systems

Multi-Robot Planning Under Uncertainty with Congestion-Aware Models (page 1314)
Charlie Street, University of Oxford
Bruno Lacerda, University of Oxford
Manuel Mühlig, Honda Research Institute Europe GmbH
Nick Hawes, University of Oxford

Games of Miners (page 1323)
Jingchang Sun, Tsinghua University
Pingzhong Tang, Tsinghua University
Yulong Zeng, ASResearch

(Return to Top)

Can Agents Learn by Analogy? An Inferable Model for PAC Reinforcement Learning (page 1332)
Yanchao Sun, University of Maryland, College Park
Furong Huang, University of Maryland, College Park

Drawing a Map of Elections in the Space of Statistical Cultures (page 1341)
Stanislaw Szufa, Jagiellonian University
Piotr Faliszewski, AGH University
Piotr Skowron, University of Warsaw
Arkadii Slinko, University of Auckland
Nimrod Talmon, Ben-Gurion University

Capturing Oracle Guided Hiders (page 1350)
Akshat Tandon, International Institute of Information Technology, Hyderabad
Kamalakar Karlapalem, International Institute of Information Technology, Hyderabad

Optimized Cost per Mille in Feeds Advertising (page 1359)
Pingzhong Tang, Tsinghua University
Xun Wang, Tsinghua University
Zihe Wang, ITCS, SUFE
Yadong Xu, Tsinghua University
Xiwang Yang, ByteDance

Differentially Private Contextual Dynamic Pricing (page 1368)
Wei Tang, Washington University in St. Louis
Chien-Ju Ho, Washington University in St. Louis
Yang Liu, University of California, Santa Cruz

An Active Learning Method for the Comparison of Agent-based Models (page 1377)
Swapna Thorve, University of Virginia
Zhihao Hu, Virginia Tech
Kiran Lakkaraju, Sandia National Laboratories
Joshua Letchford, Sandia National Laboratories
Anil Vullikanti, University of Virginia
Achla Marathe, University of Virginia
Samarth Swarup, University of Virginia

(Return to Top)

Deployment of a Plug-In Multi-Agent System for Traffic Signal Timing (page 1386)
Behnam Torabi, University of Texas at Dallas
Rym Zalila-Wenkstern, University of Texas at Dallas
Robert Saylor, City of Richardson
Patrick Ryan, City of Richardson

A Novel Individually Rational Objective In Multi-Agent Multi-Armed Bandits: Algorithms and Regret Bounds (page 1395)
Aristide C. Y. Tossou, Chalmers University
Christos Dimitrakakis, University of Oslo/Chalmers University
Jaroslaw Rzepecki, Microsoft Research
Katja Hofmann, Microsoft Research

The Effects of Autonomy and Task meaning in Algorithmic Management of Crowdwork (page 1404)
Yuushi Toyoda, Fujitsu Laboratories
Gale Lucas, University of Southern California Institute for Creative Technologies
Jonathan Gratch, University of Southern California Institute for Creative Technologies

Using Cognitive Models to Train Big Data Models with Small Data (page 1413)
J. Gregory Trafton, Naval Research Laboratory
Laura M. Hiatt, Naval Research Laboratory
Benjamin Brumback, Naval Research Laboratory
J. Malcolm McCurry, Peraton

Agent Ontology Alignment Repair through Dynamic Epistemic Logic (page 1422)
Line van den Berg, University Grenoble Alpes, Inria, CNRS, Grenoble INP, LIG
Manuel Atencia, University Grenoble Alpes, Inria, CNRS, Grenoble INP, LIG
Jčrome Euzenat, University Grenoble Alpes, Inria, CNRS, Grenoble INP, LIG

Plannable Approximations to MDP Homomorphisms: Equivariance under Actions (page 1431)
Elise van der Pol, UvA-Bosch Deltalab & University of Amsterdam
Thomas Kipf, University of Amsterdam
Frans A. Oliehoek, Delft University of Technology
Max Welling, UvA-Bosch Deltalab & University of Amsterdam

(Return to Top)

Learning Context-aware Task Reasoning for Efficient Meta Reinforcement Learning (page 1440)
Haozhe Wang, ShanghaiTech University
Jiale Zhou, ShanghaiTech University
Xuming He, ShanghaiTech University

Scalable Game-Focused Learning of Adversary Models: Data-to-Decisions in Network Security Games (page 1449)
Kai Wang, Harvard University
Andrew Perrault, Harvard University
Aditya Mate, Harvard University
Milind Tambe, Harvard University

Bayesian Nash Equilibrium in First-Price Auction with Discrete Value Distributions (page 1458)
Zihe Wang, Shanghai University of Finance and Economics
Weiran Shen, Carnegie Mellon University
Song Zuo, Google Research

The Manipulability of Centrality Measures-An Axiomatic Approach (page 1467)
Tomasz Wąs, University of Warsaw
Marcin Waniek, New York University Abu Dhabi & University of Warsaw
Talal Rahwan, New York University Abu Dhabi
Tomasz Michalak, University of Warsaw

Predicting Persuasive Effectiveness for Multimodal Behavior Adaptation using Bipolar Weighted Argument Graphs (page 1476)
Klaus Weber, Human-Centered Multimedia
Kathrin Janowski, Human-Centered Multimedia
Niklas Rach, Institute of Communication Engineering
Katharina Weitz, Human-Centered Multimedia
Wolfgang Minker, Institute of Communication Engineering
Stefan Ultes, Institute of Communication Engineering
Elisabeth Andrč, Human-Centered Multimedia

Adaptive Knowledge Transfer based on Transfer Neural Kernel Network (page 1485)
Pengfei Wei, National University of Singapore
Xinghua Qu, Nanyang Technological University
Yiping Ke, Nanyang Technological University
Tze-Yun Leong, National University of Singapore
Yew Soon Ong, Nanyang Technological University

(Return to Top)

Uncertainty Modelling in Multi-agent Information Fusion Systems (page 1494)
Jiali Weng, Southwest University
Fuyuan Xiao, Southwest University
Zehong Cao, University of Tasmania

A Performance-Based Start State Curriculum Framework for Reinforcement Learning (page 1503)
Jan Wöhlke, Bosch Center for Artificial Intelligence & University of Amsterdam
Felix Schmitt, Bosch Center for Artificial Intelligence
Herke van Hoof, University of Amsterdam

FRESH: Interactive Reward Shaping in High-Dimensional State Spaces using Human Feedback (page 1512)
Baicen Xiao, University of Washington
Qifan Lu, University of Washington
Bhaskar Ramasubramanian, University of Washington
Andrew Clark, Worcester Polytechnic Institute
Linda Bushnell, University of Washington
Radha Poovendran, University of Washington

On the Complexity of Sequential Posted Pricing (page 1521)
Tao Xiao, Shanghai Jiao Tong University
Zhengyang Liu, Beijing Institute of Technology
Wenhan Huang, Shanghai Jiao Tong University

Size-Relaxed Committee Selection under the Chamberlin-Courant Rule (page 1530)
Tao Xiao, Shanghai Jiao Tong University
Sujoy Sikdar, Washington University in St. Louis

Strategyproof Mechanisms for Activity Scheduling (page 1539)
Xinping Xu, Singapore University of Technology and Design
Minming Li, City University of Hong Kong
Lingjie Duan, Singapore University of Technology and Design

(Return to Top)

Game Theoretic Analysis for Two-Sided Matching with Resource Allocation (page 1548)
Kentaro Yahiro, Kyushu University
Makoto Yokoo, Kyushu University & RIKEN AIP

Optimal Control in Partially Observable Complex Social Systems (page 1557)
Fan Yang, University at Buffalo
Bruno Lepri, FBK
Wen Dong, University at Buffalo

Hierarchical Cooperative Multi-Agent Reinforcement Learning with Skill Discovery (page 1566)
Jiachen Yang, Georgia Institute of Technology
Igor Borovikov, Electronic Arts
Hongyuan Zha, Georgia Institute of Technology

αα-Rank: Practically Scaling α-Rank through Stochastic Optimisation (page 1575)
Yaodong Yang, Huawei Technologies R&D UK
Rasul Tutunov, Huawei Technologies R&D UK
Phu Sakulwongtana, Huawei Technologies R&D UK
Haitham Bou Ammar, Huawei Technologies R&D UK

On the Complexity of Destructive Bribery in Approval-Based Multi-winner Voting (page 1584)
Yongjie Yang, Saarland University

Report-Sensitive Spot-Checking in Peer-Grading Systems (page 1593)
Hedayat Zarkoob, University of British Columbia
Hu Fu, University of British Columbia
Kevin Leyton-Brown, University of British Columbia

(Return to Top)

The Power of Suggestion (page 1602)
Nicholas Zerbel, Oregon State University
Kagan Tumer, Oregon State University

Deep Residual Reinforcement Learning (page 1611)
Shangtong Zhang, University of Oxford
Wendelin Boehmer, University of Oxford
Shimon Whiteson, University of Oxford

Redistribution Mechanism on Networks (page 1620)
Wen Zhang, ShanghaiTech University
Dengji Zhao, ShanghaiTech University
Hanyu Chen, ShanghaiTech University

Collaborative Data Acquisition (page 1629)
Wen Zhang, ShanghaiTech University
Yao Zhang, ShanghaiTech University
Dengji Zhao, ShanghaiTech University

SwarmTalk - Towards Benchmark Software Suites for Swarm Robotics Platforms (page 1638)
Yihan Zhang, Northwestern University
Lyon Zhang, Northwestern University
Hanlin Wang, Northwestern University
Fabián E. Bustamante, Northwestern University
Michael Rubenstein, Northwestern University

META-Learning State-based Eligibility Traces for More Sample-Efficient Policy Evaluation (page 1647)
Mingde Zhao, Mila, McGill University
Sitao Luan, Mila, McGill University
Ian Porada, Mila, McGill University
Xiao-Wen Chang, McGill University
Doina Precup, McGill University, Mila, DeepMind

(Return to Top)

Competitive and Cooperative Heterogeneous Deep Reinforcement Learning (page 1656)
Han Zheng, University of Technology Sydney
Jing Jiang, University of Technology Sydney
Pengfei Wei, National University of Singapore
Guodong Long, University of Technology Sydney
Chengqi Zhang, University of Technology Sydney

Parameterized Complexity of Shift Bribery in Iterative Elections (page 1665)
Aizhong Zhou, Shandong University
Jiong Guo, Shandong University

Learning by Reusing Previous Advice in Teacher-Student Paradigm (page 1674)
Changxi Zhu, South China University of Technology
Yi Cai, South China University of Technology
Ho-fung Leung, The Chinese University of Hong Kong
Shuyue Hu, National University of Singapore

(Return to Top)

Blue Sky Idea Papers

Towards Reality: Smoothed Analysis in Computational Social Choice (page 1691)
Dorothea Baumeister, Heinrich-Heine-Universität Düsseldorf
Tobias Hogrebe, Heinrich-Heine-Universität Düsseldorf
Jörg Rothe, Heinrich-Heine-Universität Düsseldorf

A Multi-Robot Platform for the Autonomous Operation and Maintenance of Offshore Wind Farms (page 1696)
Sara Bernardini, Royal Holloway University of London
Ferdian Jovan, Royal Holloway University of London
Zhengyi Jiang, University of Manchester
Simon Watson, University of Manchester
Andrew Weightman, University of Manchester
Peiman Moradi, University of Bristol
Tom Richardson, University of Bristol
Rasoul Sadeghian, Royal College of Art
Sina Sareh, Royal College of Art

Agents are Dead. Long live Agents! (page 1701)
Virginia Dignum, Umeĺ University
Frank Dignum, Umeĺ University

(Return to Top)

New Foundations of Ethical Multiagent Systems (page 1706)
Pradeep K. Murukannaiah, Delft University of Technology
Nirav Ajmeri, North Carolina State University
Catholijn M. Jonker, Delft University of Technology
Munindar P. Singh, North Carolina State University

Research Challenges and Opportunities in Multi-Agent Path Finding and Multi-Agent Pickup and Delivery Problems (page 1711)
Oren Salzman, Technion Israel Institute of Technology
Roni Stern, Ben Gurion University of the Negev; Palo Alto Research Center

We Need Fairness and Explainability in Algorithmic Hiring (page 1716)
Candice Schumann, University of Maryland
Jeffrey S. Foster, Tufts University
Nicholas Mattei, Tulane University
John P. Dickerson, University of Maryland

Live Simulations (page 1721)
Samarth Swarup, University of Virginia
Henning S. Mortveit, University of Virginia

Multiagent Climate Change Research (page 1726)
Vahid Yazdanpanah, University of Twente
Sara Mehryar, London School of Economics
Nicholas R. Jennings, Imperial College London
Swenja Surminski, London School of Economics
Martin J. Siegert, Imperial College London
Jos van Hillegersberg, University of Twente

(Return to Top)

Extended Abstracts

Designing Truthful Contextual Multi-Armed Bandits based Sponsored Search Auctions (page 1732)
Kumar Abhishek, International Institute of Information Technology (IIIT)
Shweta Jain, Indian Institute of Technology (IIT)
Sujit Gujar, International Institute of Information Technology (IIIT)

(Return to Top)

Boolean Games: Inferring Agents' Goals Using Taxation Queries (page 1735)
Abhijin Adiga, Biocomplexity Institute and Inititative, University of Virginia
Sarit Kraus, Bar-Ilan University
S. S. Ravi, Biocomplexity Institute and Initiative, University of Virginia & University of Albany - SUNY

Leveraging Communication Topologies Between Learning Agents in Deep Reinforcement Learning (page 1738)
Dhaval Adjodah, Massachusetts Institute of Technology
Dan Calacci, Massachusetts Institute of Technology
Abhimanyu Dubey, Massachusetts Institute of Technology
Anirudh Goyal, MILA/University of Montreal
P.M. Krafft, Oxford Internet Institute
Esteban Moro, Massachusetts Institute of Technology
Alex Pentland, Massachusetts Institute of Technology

Learning Transferable Cooperative Behavior in Multi-Agent Teams (page 1741)
Akshat Agarwal, Carnegie Mellon University
Sumit Kumar, Carnegie Mellon University
Katia Sycara, Carnegie Mellon University
Michael Lewis, University of Pittsburgh

Evolving Meta-Level Reasoning with Reinforcement Learning and A* for Coordinated Multi-Agent Path-planning (page 1744)
Mona Alshehri, Imam Abdulrahman Bin Faisal University & Massey University
Napoleon Reyes, Massey University
Andre Barczak, Massey University

Privacy-Preserving Dark Pools (page 1747)
Gilad Asharov, Bar Ilan University
Tucker Hybinette Balch, J.P. Morgan AI Research
Antigoni Polychroniadou, J.P. Morgan AI Research
Manuela Veloso, J.P. Morgan AI Research

Long-Run Multi-Robot Planning With Uncertain Task Durations (page 1750)
Carlos Azevedo, Instituto Superior Técnico, University of Lisbon
Bruno Lacerda, University of Oxford
Nick Hawes, University of Oxford
Pedro Lima, Instituto Superior Técnico, University of Lisbon

(Return to Top)

The Temporary Exchange Problem (page 1753)
Haris Aziz, University of New South Wales & Data61 CSIRO
Edward Lee, University of New South Wales & Data61 CSIRO

Mechanism Design for School Choice with Soft Diversity Constraints (page 1756)
Haris Aziz, University of New South Wales Sydney & Data61 CSIRO
Serge Gaspers, University of New South Wales Sydney
Zhaohong Sun, University of New South Wales Sydney & Data61 CSIRO

Multiple Levels of Importance in Matching with Distributional Constraints (page 1759)
Haris Aziz, University of New South Wales Sydney & Data 61 CSIRO
Serge Gaspers, University of New South Wales Sydney
Zhaohong Sun, University of New South Wales Sydney & Data 61 CSIRO
Makoto Yokoo, Kyushu University

Learning Complementary Representations of the Past using Auxiliary Tasks in Partially Observable Reinforcement Learning (page 1762)
Andrea Baisero, Northeastern University
Christopher Amato, Northeastern University

Autonomous Shape Formation and Morphing in a Dynamic Environment by a Swarm of Robots (page 1765)
Vaibhav Bajaj, International Institute of Information Technology
Sachit Rao, International Institute of Information Technology

Reinforcement Learning Dynamics in the Infinite Memory Limit (page 1768)
Wolfram Barfuss, University of Leeds & Max Planck Institute for Mathematics in the Sciences

(Return to Top)

Complexity of Election Evaluation and Probabilistic Robustness (page 1771)
Dorothea Baumeister, Heinrich-Heine-Universität Düsseldorf
Tobias Hogrebe, Heinrich-Heine-Universität Düsseldorf

Irresolute Approval-based Budgeting (page 1774)
Dorothea Baumeister, Heinrich-Heine-Universität Düsseldorf
Linus Boes, Heinrich-Heine-Universität Düsseldorf
Tessa Seeger, Heinrich-Heine-Universität Düsseldorf

Hedonic Seat Arrangement Problems (page 1777)
Hans L. Bodlaender, Utrecht University
Tesshu Hanaka, Chuo University
Lars Jaffke, University of Bergen
Hirotaka Ono, Nagoya University
Yota Otachi, Kumamoto Univerisity
Tom C. van der Zanden, Maastricht University

Stable Roommate Problem With Diversity Preferences (page 1780)
Niclas Boehmer, Technische Universität Berlin
Edith Elkind, University of Oxford

Encapsulating Reactive Behaviour in Goal-Based Plans for Programming BDI Agents (page 1783)
Rafael H. Bordini, Pontifical Catholic University of Rio Grande do Sul
Rem Collier, University College of Dublin
Jomi F. Hübner, Federal University of Santa Catarina
Alessandro Ricci, University of Bologna

Finding Spatial Clusters Susceptible to Epidemic Outbreaks due to Undervaccination (page 1786)
Jose Cadena, Lawrence Livermore National Laboratory
Achla Marathe, University of Virginia
Anil Vullikanti, University of Virginia

(Return to Top)

Adaptive and Collaborative Agent-based Traffic Regulation using Behavior Trees (page 1789)
Arthur Casals, Sorbonne Université
Assia Belbachir, IPSA
Amal El Fallah-Seghrouchni, Sorbonne Université

Option-Critic in Cooperative Multi-agent Systems (page 1792)
Jhelum Chakravorty, McGill University & Mila
Patrick Nadeem Ward, McGill University & Mila
Julien Roy, University of Montreal & Mila
Maxime Chevalier-Boisvert, Mila
Sumana Basu, McGill University & Mila
Andrei Lupu, McGill University & Mila
Doina Precup, McGill University, Mila, & DeepMind

The Price of Anarchy of Self-Selection in Tullock Contests (page 1795)
Hau Chan, University of Nebraska-Lincoln
David C. Parkes, Harvard University
Karim R. Lakhani, Harvard Business School

Human-in-the-loop Planning and Monitoring of Swarm Search and Service Missions (page 1798)
Meghan Chandarana, Carnegie Mellon University
Michael Lewis, University of Pittsburgh
Katia Sycara, Carnegie Mellon University
Sebastian Scherer, Carnegie Mellon University

A New Framework for Multi-Agent Reinforcement Learning - Centralized Training and Exploration with Decentralized Execution via Policy Distillation (page 1801)
Gang Chen, Victoria University of Wellington

Aggregation of Support-Relations of Bipolar Argumentation Frameworks (page 1804)
Weiwei Chen, Sun Yat-sen University

(Return to Top)

Social Structure Emergence: A Multi-agent Reinforcement Learning Framework for Relationship Building (page 1807)
Yang Chen, The University of Auckland
Jiamou Liu, The University of Auckland
He Zhao, Beijing Institute of Technology
Hongyi Su, Beijing Institute of Technology

The Fair Contextual Multi-Armed Bandit (page 1810)
Yifang Chen, University of Southern California
Alex Cuellar, University of Southern California
Haipeng Luo, University of Southern California
Jignesh Modi, University of Southern California
Heramb Nemlekar, University of Southern California
Stefanos Nikolaidis, University of Southern California

Limiting the Deviation Incentives in Resource Sharing Networks (page 1813)
Yukun Cheng, Suzhou University of Science and Technology
Xiaotie Deng, Peking University
Yuhao Li, Peking University

An Abstract Framework for Agent-Based Explanations in AI (page 1816)
Giovanni Ciatto, University of Bologna
Davide Calvaresi, HES-SO
Michael I. Schumacher, HES-SO
Andrea Omicini, University of Bologna

Fear of Punishment Promotes the Emergence of Cooperation and Enhanced Social Welfare in Social Dilemmas (page 1819)
Theodor Cimpeanu, Teesside University
The Anh Han, Teesside University

Voting with Random Classifiers (VORACE) (page 1822)
Cristina Cornelio, IBM Research
Michele Donini, Amazon
Andrea Loreggia, European University Institute
Maria Silvia Pini, University of Padova
Francesca Rossi, IBM Research

(Return to Top)

Translating Embedding with Local Connection for Knowledge Graph Completion (page 1825)
Zeyuan Cui, Shandong University
Shijun Liu, Shandong University
Li Pan, Shandong University
Qiang He, Swinburne University of Technology

Distributed, Automated Calibration of Agent-based Model Parameters and Agent Behaviors (page 1828)
Matteo D'Auria, Universitŕ degli Studi di Salerno
Eric O. Scott, George Mason University
Rajdeep Singh Lather, George Mason University
Javier Hilty, George Mason University
Sean Luke, George Mason University

Distributed Reinforcement Learning for Cooperative Multi-Robot Object Manipulation (page 1831)
Guohui Ding, University of Colorado Boulder
Joewie J. Koh, University of Colorado Boulder
Kelly Merckaert, Vrije Universiteit Brussel
Bram Vanderborght, Vrije Universiteit Brussel
Marco M. Nicotra, University of Colorado Boulder
Christoffer Heckman, University of Colorado Boulder
Alessandro Roncone, University of Colorado Boulder
Lijun Chen, University of Colorado Boulder

Decomposed Deep Reinforcement Learning for Robotic Control (page 1834)
Yinzhao Dong, Dalian University of Technology
Chao Yu, Sun Yat-Sen University
Paul Weng, Shanghai Jiao Tong University
Ahmed Maustafa, Nagoya Institute of Technology
Hui Cheng, Sun Yat-Sen University
Hongwei Ge, Dalian University of Technology

Computationally Grounded Quantitative Trust with Time (page 1837)
Nagat Drawel, Concordia University
Jamal Bentahar, Concordia University
Hongyang Qu, Shefield University

Microbribery in Group Identification (page 1840)
Gabor Erdelyi, University of Canterbury
Yongjie Yang, Saarland University

(Return to Top)

Decentralized Task Assignment for Multi-item Pickup and Delivery in Logistic Scenarios (page 1843)
Alessandro Farinelli, University of Verona
Antonello Contini, University of Verona
Davide Zorzi, University of Verona

Distance Hedonic Games (page 1846)
Michele Flammini, Gran Sasso Science Institute
Bojana Kodric, Gran Sasso Science Institute
Martin Olsen, Aarhus University
Giovanna Varricchio, Gran Sasso Science Institute

Ballooning Multi-Armed Bandits (page 1849)
Ganesh Ghalme, Indian Institute of Science
Swapnil Dhamal, Chalmers University of Technology
Shweta Jain, Indian Institute of Technology Ropar
Sujit Gujar, International Institute of Information Technology, Hyderabad
Y. Narahari, Indian Institute of Science

Cluster-Based Social Reinforcement Learning (page 1852)
Mahak Goindani, Purdue University
Jennifer Neville, Purdue University

Multi-agent Adversarial Inverse Reinforcement Learning with Latent Variables (page 1855)
Nate Gruver, Stanford University
Jiaming Song, Stanford University
Mykel J. Kochenderfer, Stanford University
Stefano Ermon, Stanford University

Networked Multi-Agent Reinforcement Learning with Emergent Communication (page 1858)
Shubham Gupta, Indian Institute of Science
Rishi Hazra, Indian Institute of Science
Ambedkar Dukkipati, Indian Institute of Science

(Return to Top)

Winning an Election: On Emergent Strategic Communication in Multi-Agent Networks (page 1861)
Shubham Gupta, Indian Institute of Science
Ambedkar Dukkipati, Indian Institute of Science

Matching Affinity Clustering: Improved Hierarchical Clustering at Scale with Guarantees (page 1864)
MohammadTaghi Hajiaghayi, University of Maryland, College Park
Marina Knittel, University of Maryland, College Park

Automating Coordinated Autonomous Vehicle Control (page 1867)
Allen Huang, University of Cape Town
Geoff Nitschke, University of Cape Town

Anchor Attention for Hybrid Crowd Forecasts Aggregation (page 1869)
Yuzhong Huang, University of Southern California
Andrés Abeliuk, University of Southern California
Fred Morstatter, University of Southern California
Pavel Atanasov, Pytho, LLC.
Aram Galstyan, University of Southern California

Mastering Basketball With Deep Reinforcement Learning: An Integrated Curriculum Training Approach (page 1872)
Hangtian Jia, Netease Fuxi AI Lab
Chunxu Ren, Netease Fuxi AI Lab
Yujing Hu, Netease Fuxi AI Lab
Yingfeng Chen, Netease Fuxi AI Lab
Tangjie Lv, Netease Fuxi AI Lab
Changjie Fan, Netease Fuxi AI Lab
Hongyao Tang, Tianjin University
Jianye Hao, Tianjin University

Multi-agent Path Planning based on MA-RRT* Fixed Nodes (page 1875)
Jinmingwu Jiang, Chongqing University
Kaigui Wu, Chongqing University

(Return to Top)

An Agent-Based Model for Trajectory Modelling in Shared Spaces: A Combination of Expert-Based and Deep Learning Approaches (page 1878)
Fatema T. Johora, Clausthal University of Technology
Hao Cheng, Leibniz University Hannover
Jörg P. Müller, Clausthal University of Technology
Monika Sester, Leibniz University Hannover

Anchoring Theory in Sequential Stackelberg Games (page 1881)
Jan Karwowski, Warsaw University of Technology
Jacek Mańdziuk, Warsaw University of Technology
Adam Żychowski, Warsaw University of Technology

Efficient Hybrid Fault Detection for Autonomous Robots (page 1884)
Eliahu Khalastchi, College of Management Academic Studies
Meir Kalech, Ben-Gurion University of the Negev

Silly Rules Improve the Capacity of Agents to Learn Stable Enforcement and Compliance Behaviors (page 1887)
Raphael Koster, DeepMind
Dylan Hadfield-Menell, University of California, Berkeley
Gillian K. Hadfield, University of Toronto & OpenAI
Joel Z. Leibo, DeepMind

Signaling Friends and Head-Faking Enemies Simultaneously: Balancing Goal Obfuscation and Goal Legibility (page 1889)
Anagha Kulkarni, Arizona State University
Siddharth Srivastava, Arizona State University
Subbarao Kambhampati, Arizona State University

Deep Reinforcement Learning for Market Making (page 1892)
Pankaj Kumar, Copenhagen Business School

(Return to Top)

Computing the Shapley Value for Ride-Sharing and Routing Games (page 1895)
Chaya Levinger, Ariel University
Noam Hazon, Ariel University
Amos Azaria, Ariel University

Lifelong Multi-Agent Path Finding in Large-Scale Warehouses (page 1898)
Jiaoyang Li, University of Southern California
Andrew Tinka, Amazon Robotics
Scott Kiesel, Amazon Robotics
Joseph W. Durham, Amazon Robotics
T. K. Satish Kumar, University of Southern California
Sven Koenig, University of Southern California

Graph Neural Networks for Decentralized Path Planning (page 1901)
Qingbiao Li, University of Cambridge
Fernando Gama, University of Pennsylvania
Alejandro Ribeiro, University of Pennsylvania
Amanda Prorok, University of Cambridge

PANDA: Privacy-Aware Double Auction for Divisible Resources without a Mediator (page 1904)
Bingyu Liu, Illinois Institute of Technology
Shangyu Xie, Illinois Institute of Technology
Yuan Hong, Illinois Institute of Technology

Two-sided Auctions with Budgets: Fairness, Incentives and Efficiency (page 1907)
Xiang Liu, Southeast University
Weiwei Wu, Southeast University
Minming Li, City University of Hong Kong
Wanyuan Wang, Southeast University

Robust Following with Hidden Information in Travel Partners (page 1910)
Shih-Yun Lo, University of Texas at Austin
Elaine Schaertl Short, Tufts University
Andrea L. Thomaz, University of Texas at Austin

(Return to Top)

A Decentralized Multi-Agent Coordination Method for Dynamic and Constrained Production Planning (page 1913)
Marin Lujak, IMT Lille Douai University Lille
Alberto Fernandez, Universidad Rey Juan Carlos
Eva Onaindia, Valencian Research Institute for AI

Normalizing Flow Model for Policy Representation in Continuous Action Multi-agent Systems (page 1916)
Xiaobai Ma, Stanford University
Jayesh K. Gupta, Stanford University
Mykel J. Kochenderfer, Stanford University

Genetic Deep Reinforcement Learning for Mapless Navigation (page 1919)
Enrico Marchesini, University of Verona
Alessandro Farinelli, University of Verona

A Game Theoretic Approach For k-Core Minimization (page 1922)
Sourav Medya, Northwestern University
Tianyi Ma, University of California, Los Angeles
Arlei Silva, University of California, Santa Barbara
Ambuj Singh, University of California, Santa Barbara

Modified Actor-Critics (page 1925)
Erinc Merdivan, AIT Austrian Institute of Technology & CentraleSupélec
Sten Hanke, FH Joanneum Gesellschaft mbH
Matthieu Geist, Google Research

Multi-Vehicle Mixed Reality Reinforcement Learning for Autonomous Multi-Lane Driving (page 1928)
Rupert Mitchell, University of Cambridge
Jenny Fletcher, University of Cambridge
Jacopo Panerati, University of Cambridge
Amanda Prorok, University of Cambridge

(Return to Top)

Maximizing Plan Legibility in Stochastic Environments (page 1931)
Shuwa Miura, University of Massachusetts, Amherst
Shlomo Zilberstein, University of Massachusetts, Amherst

Cooperative Real-Time Inertial Parameter Estimation (page 1934)
Marina Moreira, NASA Ames Research Center
Brian Coltin, KBR Inc. & NASA Ames Research Center
Rodrigo Ventura, Instituto Superior Técnico

Towards a Value-driven Explainable Agent for Collective Privacy (page 1937)
Francesca Mosca, King's College London
Jose M. Such, King's College London
Peter McBurney, King's College London

Argumentation is More Important than Appearance for Designing Culturally Tailored Virtual Agents (page 1940)
Prasanth Murali, Northeastern University
Ameneh Shamekhi, Northeastern University
Dhaval Parmar, Northeastern University
Timothy Bickmore, Northeastern University

Mining International Political Norms from the GDELT Database (page 1943)
Rohit Murali, Indian Institute of Science
Suravi Patnaik, Sponsa Limited
Stephen Cranefield, University of Otago

Robust Self-organization in Games: Symmetries, Conservation Laws and Dimensionality Reduction (page 1946)
Sai Ganesh Nagarajan, Singapore University of Technology and Design
David Balduzzi, Google DeepMind
Georgios Piliouras, Singapore University of Technology and Design

(Return to Top)

Mini-batch Bayesian Inverse Reinforcement Learning for Multiple Dynamics (page 1949)
Yusuke Nakata, Chiba University
Sachiyo Arai, Chiba University

A Study of Incentive Compatibility and Stability Issues in Fractional Matchings (page 1951)
Shivika Narang, Indian Institute of Science
Yadati Narahari, Indian Institute of Science

Conditional Updates of Answer Set Programming and Its Application in Explainable Planning (page 1954)
Van Nguyen, New Mexico State University
Tran Cao Son, New Mexico State University
Vasileiou Loukas Stylianos, Washington University in St. Louis
William Yeoh, Washington University in St. Louis

Explicit Modelling of Resources for Multi-Agent MicroServices using the CArtAgO Framework (page 1957)
Eoin O'Neill, University College Dublin
David Lillis, University College Dublin
Gregory M.P. O'Hare, University College Dublin
Rem W. Collier, University College Dublin

Vulcano: Operational Fire Suppression Management Using Deep Reinforcement Learning (page 1960)
Cristobal Pais, University of California, Berkeley

Hierarchical Reinforcement Learning with Integrated Discovery of Salient Subgoals (page 1963)
Shubham Pateria, Nanyang Technological University
Budhitama Subagdja, Nanyang Technological University
Ah Hwee Tan, Nanyang Technological University

(Return to Top)

Sequential Advertising Agent with Interpretable User Hidden Intents (page 1966)
Zhaoqing Peng, Alibaba Group
Junqi Jin, Alibaba Group
Lan Luo, University of Southern California
Yaodong Yang, University College London
Rui Luo, University College London
Jun Wang, University College London
Weinan Zhang, Shanghai Jiao Tong University
Miao Xu, Alibaba Group
Chuan Yu, Alibaba Group
Tiejian Luo, University of Chinese Academy of Sciences
Han Li, Alibaba Group
Jian Xu, Alibaba Group
Kun Gai, Alibaba Group

Discovering Imperfectly Observable Adversarial Actions using Anomaly Detection (page 1969)
Olga Petrova, Avast Software
Karel Durkota, Czech Technical University in Prague
Galina Alperovich, Avast Software
Karel Horak, Avast Software
Michal Najman, Avast Software
Branislav Bosansky, Avast Software & Czech Technical University in Prague
Viliam Lisy, Avast Software & Czech Technical University in Prague

Aplib: An Agent Programming Library for Testing Games (page 1972)
I. S. W. B. Prasetya, Utrecht University
Mehdi Dastani, Utrecht University

Modeling Disinformation and the Effort to Counter It: A Cautionary Tale of When the Treatment Can Be Worse Than the Disease (page 1975)
Amirarsalan Rajabi, University of Central Florida
Chathika Gunaratne, University of Central Florida
Alexander V. Mantzaris, University of Central Florida
Ivan Garibay, University of Central Florida

GUESs: Generative modeling of Unknown Environments and Spatial Abstraction for Robots (page 1978)
Francesco Riccio, Sapienza University of Rome
Roberto Capobianco, Sapienza University of Rome
Daniele Nardi, Sapienza University of Rome

Continuous Influence Maximisation for the Voter Dynamics: Is Targeting High-Degree Nodes a Good Strategy? (page 1981)
Guillermo Romero Moreno, University of Southampton
Long Tran-Thanh, University of Southampton
Markus Brede, University of Southampton

(Return to Top)

Mitigating the Negative Side Effects of Reasoning with Imperfect Models: A Multi-Objective Approach (page 1984)
Sandhya Saisubramanian, University of Massachusetts, Amherst
Ece Kamar, Microsoft Research
Shlomo Zilberstein, University of Massachusetts, Amherst

ExTra: Transfer-guided Exploration (page 1987)
Anirban Santara, Indian Institute of Technology Kharagpur
Rishabh Madan, University of Washington
Pabitra Mitra, Indian Institute of Technology Kharagpur
Balaraman Ravindran, Indian Institute of Technology Madras

C-CoCoA: A Continuous Cooperative Constraint Approximation Algorithm to Solve Functional DCOPs (page 1990)
Amit Sarker, University of Dhaka
Abdullahil Baki Arif, University of Dhaka
Moumita Choudhury, University of Dhaka
Md. Mosaddek Khan, University of Dhaka

Heuristic Strategies in Uncertain Approval Voting Environments (page 1993)
Jaelle Scheuerman, Tulane University
Jason L. Harman, Louisiana State University
Nicholas Mattei, Tulane University
K. Brent Venable, University of West Florida

Not all Mistakes are Equal (page 1996)
Murat Sensoy, Blue Prism AI Labs
Maryam Saleki, Ozyegin University
Simon Julier, University College London
Reyhan Aydoğan, Ozyegin University
John Reid, Blue Prism AI Labs

On-line Estimators for Ad-hoc Task Allocation (page 1999)
Elnaz Shafipour Yourdshahi, Lancaster University
Matheus Aparecido do Carmo Alves, University of Săo Paulo (USP)
Leandro Soriano Marcolino, Lancaster University
Plamen Angelov, Lancaster University

(Return to Top)

Theme Park Simulation based on Questionnaires for Maximizing Visitor Surplus (page 2002)
Hitoshi Shimizu, NTT Communication Science Laboratories
Tatsushi Matsubayashi, NTT Communication Science Laboratories
Akinori Fujino, NTT Communication Science Laboratories
Hiroshi Sawada, NTT Communication Science Laboratories

Fair Cake-Cutting Algorithms with Real Land-Value Data (page 2005)
Itay Shtechman, The Open University of Israel
Rica Gonen, The Open University of Israel
Erel Segal-Halevi, Ariel University

BitcoinF: Achieving Fairness For Bitcoin In Transaction Fee Only Model (page 2008)
Shoeb Siddiqui, International Institute of Information Technology
Ganesh Vanahalli, International Institute of Information Technology
Sujit Gujar, International Institute of Information Technology

An Axiomatic Approach to Truth Discovery (page 2011)
Joseph Singleton, Cardiff University
Richard Booth, Cardiff University

Robust Market Making via Adversarial Reinforcement Learning (page 2014)
Thomas Spooner, University of Liverpool
Rahul Savani, University of Liverpool

Analyzing the Effects of Memory Biases and Mood Disorders on Social Performance (page 2017)
Nanda Kishore Sreenivas, Oracle
Shrisha Rao, International Institute of Information Technology - Bangalore

(Return to Top)

Neural MMO v1.3: A Massively Multiagent Game Environment for Training and Evaluating Neural Networks (page 2020)
Joseph Suarez, Massachusetts Institute of Technology
Yilun Du, Massachusetts Institute of Technology
Igor Mordach, Google Brain
Phillip Isola, Massachusetts Institute of Technology

Restricted Domains of Dichotomous Preferences with Possibly Incomplete Information (page 2023)
Zoi Terzopoulou, Institute for Logic, Language and Computation
Alexander Karpov, National Research University Higher School of Economics, Institute of Control Sciences of Russian Academy of Sciences
Svetlana Obraztsova, Nanyang Technological University Singapore

Verification-Guided Tree Search (page 2026)
Alvaro Velasquez, Air Force Research Laboratory
Daniel Melcer, Northeastern University

Thompson Sampling for Factored Multi-Agent Bandits (page 2029)
Timothy Verstraeten, Vrije Universiteit Brussel
Eugenio Bargiacchi, Vrije Universiteit Brussel
Pieter J.K. Libin, Vrije Universiteit Brussel
Diederik M. Roijers, HU University of Applied Sciences Utrecht
Ann Nowé, Vrije Universiteit Brussel

Too Many Cooks: Coordinating Multi-agent Collaboration Through Inverse Planning (page 2032)
Rose E. Wang, Massachusetts Institute of Technology
Sarah A. Wu, Massachusetts Institute of Technology
James A. Evans, University of Chicago
Joshua B. Tenenbaum, Massachusetts Institute of Technology
David C. Parkes, Harvard University
Max Kleiman-Weiner, Harvard University, MIT, & Diffeo

Online Algorithms for Multi-shop Ski Rental with Machine Learned Predictions (page 2035)
Shufan Wang, Binghamton University, the State University of New York
Jian Li, Binghamton University, the State University of New York

(Return to Top)

An Interpretable Multimodal Visual Question Answering System using Attention-based Weighted Contextual Features (page 2038)
Yu Wang, Samsung Research America
Yilin Shen, Samsung Research America
Hongxia Jin, Samsung Research America

Automatic Synthesis of Generalized Winning Strategy of Impartial Combinatorial Games (page 2041)
Kaisheng Wu, Jinan University
Yong Qiao, Jinan University
Kaidong Chen, Jinan University
Fei Rong, Jinan Uniersity
Liangda Fang, Jinan University
Zhao-Rong Lai, Jinan University
Qian Dong, Jinan University
Liping Xiong, South China Normal University

Embedding Preference Elicitation Within the Search for DCOP Solutions (page 2044)
Yuanming Xiao, Washington University in St. Louis
Atena M. Tabakhi, Washington University in St. Louis
William Yeoh, Washington University in St. Louis

A Supervised Topic Model Approach to Learning Effective Styles within Human-Agent Negotiation (page 2047)
Yuyu Xu, Northeastern University
David Jeong, University of Southern California
Pedro Sequeira, SRI International
Jonathan Gratch, Institute for Creative Technologies
Javed Aslam, Northeastern University
Stacy Marsella, Northeastern University

An Information Distribution Method for Avoiding Hunting Phenomenon in Theme Parks (page 2050)
Hiroaki Yamada, Fujitsu Laboratories Ltd.
Naoyuki Kamiyama, Kyushu University & JST, PRESTO

Efficient Deep Reinforcement Learning through Policy Transfer (page 2053)
Tianpei Yang, Tianjin University
Jianye Hao, Tianjin University & Noah's Ark Lab, Huawei
Zhaopeng Meng, Tianjin University
Zongzhang Zhang, Nanjing University
Yujing Hu, Fuxi AI Lab in Netease
Yingfeng Chen, Fuxi AI Lab in Netease
Changjie Fan, Fuxi AI Lab in Netease
Weixun Wang, Tianjin University
Zhaodong Wang, Washington State University
Jiajie Peng, Northwestern Polytechnical University

(Return to Top)

Task Coordination in Multiagent Systems (page 2056)
Vahid Yazdanpanah, University of Twente
Mehdi Dastani, Utrecht University
Shaheen Fatima, Loughborough University
Nicholas R. Jennings, Imperial College London
Devrim M. Yazan, University of Twente
Henk Zijm, University of Twente

The Sequential Online Chore Division Problem - Definition and Application (page 2059)
Harel Yedidsion, University of Texas at Austin
Shani Alkoby, Ariel University
Peter Stone, University of Texas at Austin

A Computational Model of Hurricane Evacuation Decision (page 2062)
Nutchanon Yongsatianchot, Northeastern University
Stacy Marsella, Northeastern University

Interactive RL via Online Human Demonstrations (page 2065)
Chao Yu, Sun Yat-Sen University
Tianpei Yang, New York University
Wenxuan Zhu, Dalian University of Technology
Yinzhao Dong, Dalian University of Technology
Guangliang Li, Ocean University of China

CoMet: A Meta Learning-Based Approach for Cross-Dataset Labeling Using Co-Training (page 2068)
Guy Zaks, Ben-Gurion University
Gilad Katz, Ben-Gurion University

Explainable and Contextual Preferences based Decision Making with Assumption-based Argumentation for Diagnostics and Prognostics of Alzheimer's Disease (page 2071)
Zhiwei Zeng, Nanyang Technological University
Zhiqi Shen, Nanyang Technological University
Jing Jih Chin, Nanyang Technological University
Cyril Leung, The University of British Columbia
Yu Wang, Alibaba Group DAMO Academy AI Center
Ying Chi, Alibaba Group DAMO Academy AI Center
Chunyan Miao, Nanyang Technological University

(Return to Top)

A POMDP-based Method for Analyzing Blockchain System Security Against Long Delay Attack: (Extended Abstract) (page 2074)
Shuangfeng Zhang, Northeastern University
Yuan Liu, Northeastern University
Xingren Chen, Northeastern University
Xin Zhou, Nanyang Technological University

Learning to Cooperate: Application of Deep Reinforcement Learning for Online AGV Path Finding (page 2077)
Yi Zhang, Cainiao Network
Yu Qian, Cainiao Network
Yichen Yao, Cainiao Network
Haoyuan Hu, Cainiao Network
Yinghui Xu, Cainiao Network

Opponent Modelling for Reinforcement Learning in Multi-Objective Normal Form Games (page 2080)
Yijie Zhang, Universiteit van Amsterdam
Roxana Rădulescu, Vrije Universiteit Brussel
Patrick Mannion, National University of Ireland Galway
Diederik M. Roijers, HU University of Applied Sciences
Ann Nowé, Vrije Universiteit Brussel

Integrating Independent and Centralized Multi-agent Reinforcement Learning for Traffic Signal Network Optimization (page 2083)
Zhi Zhang, Georgia Institute of Technology
Jiachen Yang, Georgia Institute of Technology
Hongyuan Zha, Georgia Institute of Technology

Coalitional Games with Stochastic Characteristic Functions Defined by Private Types (page 2086)
Dengji Zhao, ShanghaiTech University
Yiqing Huang, ShanghaiTech University
Liat Cohen, Ben-Gurion University of the Negev
Tal Grinshpoun, Ariel University

A Generic Metaheuristic Approach to Sequential Security Games (page 2089)
Adam Żychowski, Warsaw University of Technology
Jacek Mandziuk, Warsaw University of Technology

 

Demonstrations

(Return to Top)

A Framework for Collaborative and Interactive Agent-oriented Developer Operations (page 2092)
Cleber Jorge Amaral, Instituto Federal de Santa Catarina (IFSC)
Timotheus Kampik, Umeĺ University
Stephen Cranefield, University of Otago

Hierarchical and Non-Hierarchical Multi-Agent Interactions Based on Unity Reinforcement Learning (page 2095)
Zehong Cao, University of Tasmania
Kaichiu Wong, University of Tasmania
Quan Bai, University of Tasmania
Chin-Teng Lin, University of Technology Sydney

A Consensus-based Group Decision Support System using a Multi-Agent MicroServices Approach (page 2098)
Joăo Carneiro, GECAD, Polytechnic of Porto
Rui Andrade, GECAD, Polytechnic of Porto
Patrícia Alves, GECAD, Polytechnic of Porto
Luís Conceiçăo, GECAD, Polytechnic of Porto
Paulo Novais, Algoritmi, University of Minho
Goreti Marreiros, GECAD, Polytechnic of Porto

AI-assisted Schedule Explainer for Nurse Rostering (page 2101)
Kristijonas Čyras, Ericsson Research
Amin Karamlou, University of Austin
Myles Lee, Oracle Inc.
Dimitrios Letsios, King's College London
Ruth Misener, Imperial College London
Francesca Toni, Imperial College London

Coordination of Prosumer Agents via Distributed Optimal Power Flow: An Edge Computing Hardware Prototype (page 2104)
Daniel Gebbran, University of Sydney
Gregor Verbič, University of Sydney
Archie C. Chapman, University of Queensland
Sleiman Mhanna, University of Melbourne

Trading Agent Competition with Autonomous Economic Agents (page 2107)
David Minarsch, Fetch.ai
Marco Favorito, Fetch.ai
Ali Hosseini, Fetch.ai
Jonathan Ward, Fetch.ai

(Return to Top)

MsATL: A Tool for SAT-Based ATL Satisfiability Checking (page 2111)
Artur Niewiadomski, Siedlce University
Magdalena Kacprzak, Bialystok University of Technology
Damian Kurpiewski, ICS PAS
Michał Knapik, ICS PAS
Wojciech Penczek, ICS PAS
Wojciech Jamroga, ICS PAS & University of Luxembourg

MARTINE: Multi-Agent based Real-Time INfrastructure for Energy (page 2114)
Tiago Pinto, GECAD/Polytechnic of Porto
Luis Gomes, GECAD/Polytechnic of Porto
Pedro Faria, GECAD/Polytechnic of Porto
Filipe Sousa, GECAD/Polytechnic of Porto
Zita Vale, Polytechnic of Porto

User-Models to Drive an Adaptive Virtual Advisor (page 2117)
Hedieh Ranjbartabar, Macquarie University
Deborah Richards, Macquarie University
Ayse Aysin Bilgin, Macquarie University
Cat Kutay, University of Technology Sydney
Samuel Mascarenhas, INESC-ID & Institute Superior Técnico

DALI: An Agent-Plug-In System to "Smartify" Conventional Traffic Control Systems (page 2120)
Behnam Torabi, University of Texas at Dallas
Rym Zalila-Wenkstern, University of Texas at Dallas

VerSecTis - An Agent based Model Checker for Security Protocols (page 2123)
Agnieszka M. Zbrzezny, University of Warmia and Mazury
Andrzej Zbrzezny, Jan Dlugosz University
Sabina Szymoniak, Czestochowa University of Technology
Olga Siedlecka-Lamch, Czestochowa University of Technology
Miroslaw Kurkowski, Cardinal St. Wyszynski University

(Return to Top)

JAAMAS Track Papers

VERIFCAR: A Framework for Modeling and Model checking Communicating Autonomous Vehicles (page 2126)
Johan Arcile, IBISC, Univ Evry, Université Paris-Saclay
Raymond Devillers, ULB
Hanna Klaudel, IBISC, Univ Evry, Université Paris-Saclay

Strategyproof Multi-Item Exchange Under Single-Minded Dichotomous Preferences (page 2128)
Haris Aziz, UNSW Sydney and Data61 CSIRO

Sequential Voting in Multi-agent Soft Constraint Aggregation (page 2131)
Cristina Cornelio, IBM Research
Maria Silvia Pini, University of Padova
Francesca Rossi, IBM Research
K. Brent Venable, IHMC & University of West Florida

(Return to Top)

Strategic Negotiations for Extensive-Form Games (page 2134)
Dave de Jonge, IIIA-CSIC
Dongmo Zhang, Western Sydney University

Inferring True Voting Outcomes in Homophilic Social Networks (page 2137)
John A. Doucette, New College of Florida and Bloomberg Inc.
Alan Tsang, National University of Singapore
Hadi Hosseini, Rochester Institute of Technology
Kate Larson, University of Waterloo
Robin Cohen, University of Waterloo

COMBIMA: Truthful, Budget Maintaining, Dynamic Combinatorial Market (page 2140)
Rica Gonen, The Open University of Israel
Ozi Egri, The Open University of Israel

Probabilistic Physical Search on General Graphs: Approximations and Heuristics (page 2143)
Noam Hazon, Ariel University
Mira Gonen, Ariel University

A Very Condensed Survey and Critique of Multiagent Deep Reinforcement Learning (page 2146)
Pablo Hernandez-Leal, Borealis AI
Bilal Kartal, Borealis AI
Matthew E. Taylor, Borealis AI

A Formal Framework for Reasoning about Opportunistic Propensity in Multi-agent Systems (page 2149)
Jieting Luo, Zhejiang University
John-Jules Meyer, Utrecht University
Max Knobbout, Triple

Norm Emergence in Multiagent Systems: A Viewpoint Paper (page 2152)
Andreasa Morris-Martin, University of Bath
Marina De Vos, University of Bath
Julian Padget, University of Bath

Solving the Fair Electric Load Shedding Problem in Developing Countries (page 2155)
Olabambo I. Oluwasuji, University of Southampton
Obaid Malik, University of Southampton
Jie Zhang, University of Southampton
Sarvapali D. Ramchurn, University of Southampton

Multi-Objective Multi-Agent Decision Making: A Utility-based Analysis and Survey (page 2158)
Roxana Rădulescu, Vrije Universiteit Brussel
Patrick Mannion, National University of Ireland Galway
Diederik M. Roijers, HU University of Appl. Sci. Utrecht
Ann Nowé, Vrije Universiteit Brussel

Why, Who, What, When and How about Explainability in Human-Agent Systems (page 2161)
Avi Rosenfeld, Jerusalem College of Technology
Ariella Richardson, Jerusalem College of Technology

Agents Teaching Agents: A Survey on Inter-agent Transfer Learning (page 2165)
Felipe Leno Da Silva, Advanced Institute for AI
Garrett Warnell, Army Research Laboratory
Anna Helena Reali Costa, University of Săo Paulo
Peter Stone, The University of Texas at Austin

(Return to Top)

Doctoral Consortium

Long-Run Multi-Robot Planning Under Uncertain Task Durations (page 2168)
Carlos Azevedo, Institute For Systems and Robotics, Instituto Superior Técnico, University of Lisbon

Modeling and Comparing Robot Behaviors for Anomaly Detection (page 2171)
Davide Azzalini, Politecnico di Milano

Competence-Aware Systems for Long-Term Autonomy (page 2174)
Connor Basich, University of Massachusetts, Amherst

Computer-aided Reasoning about Collective Decision Making (page 2176)
Arthur Boixel, University of Amsterdam

Vision for Decisions: Utilizing Uncertain Real-Time Information and Signaling for Conservation (page 2179)
Elizabeth Bondi, Harvard University

Efficiency and Fairness of Resource Utilisation under Uncertainty (page 2182)
Jan Buermann, University of Southampton

Computing Desirable Partitions in Coalition Formation Games (page 2185)
Martin Bullinger, Technische Universität München

Cost Effective Interventions in Complex Networks Using Agent-Based Modelling and Simulations (page 2188)
Theodor Cimpeanu, Teesside University

(Return to Top)

A Theoretical Framework for Self-Organized Task Allocation in Large Swarms (page 2191)
John Harwell, University of Minnesota

Adaptive Agent-Based Simulation for Individualized Training (page 2193)
Johan Källström, Linköping University

Decentralised Runtime Norm Synthesis (page 2196)
Andreasa Morris-Martin, University of Bath

Value-Aligned and Explainable Agents for Collective Decision Making: Privacy Application (page 2199)
Francesca Mosca, King's College London

Reinforcement Learning Algorithms for Autonomous Adaptive Agents (page 2201)
Sindhu Padakandla, Indian Institute of Science

Achieving Emergent Governance in Competitive Multi-Agent Systems (page 2204)
Michael Pernpeintner, University of Mannheim

A Utility-Based Perspective on Multi-Objective Multi-Agent Decision Making (page 2207)
Roxana Rădulescu, Vrije Universiteit Brussel

Computational Methods for Simulating Biased Agents (page 2209)
Jaelle Scheuerman, Tulane University

Truth Discovery: Who to Trust and What to Believe (page 2211)
Joseph Singleton, Cardiff University

Algorithmic Fairness for Networked Algorithms (page 2214)
Ana-Andreea Stoica, Columbia University

Towards Multi-Robot Coordination under Temporal Uncertainty (page 2217)
Charlie Street, University of Oxford

(Return to Top)

New Challenges in Matching with Constraints (page 2219)
Zhaohong Sun, University of New South Wales Sydney & Data61 CSIRO

Incomplete Opinions in Collective Decision Making (page 2222)
Zoi Terzopoulou, Institute for Logic, Language and Computation

Multimodal Representation Learning for Robotic Cross-Modality Policy Transfer (page 2225)
Miguel Vasco, INESC-ID & Instituto Superior Técnico, University of Lisbon

Balance Between Scalability and Optimality in Network Security Games (page 2228)
Kai Wang, Harvard University

Implementing Securities Based Decision Markets with Stochastic Decision Rules (page 2231)
Wenlong Wang, Massey University

Incentive Mechanisms for Data Privacy Preservation and Pricing (page 2234)
Mengxiao Zhang, The University of Auckland