Paper Sessions at AAMAS-2021
The information on this page might be out of date. Please refer to the detailed programme on the AAMAS website instead.
Below you will find the draft schedule for the paper sessions at AAMAS-2021. This concerns all full papers in the Main Track, as well as all papers in the Blue Sky Ideas Track and the JAAMAS Track.
Disclaimer:
While we expect this to be the final schedule, we reserve the right to still make minor changes without specifically notifying the authors affected (other than by updating this page). The official schedule will get published on the AAMAS website soon. Please understand that we won't be able to process requests for changes in the schedule. It already respects all author constraints communicated to us through the scheduling form, and we did our best to design a programme with thematically coherent sessions (and we are aware of its imperfections). Please note that author names and paper titles for this draft schedule were taken from the submission system; for the final version we will use the (more accurate) data collected for the proceedings instead.
How will paper sessions work this year?
Participants will get access to the papers and the pre-recorded videos well ahead of the start of the conference. They will have the opportunity to enter comments and questions through a chat interface. Others will be able to upvote the most interesting questions. The live sessions scheduled here are intended for discussion (just under 15 minutes per paper). The authors of each paper start their part of the discussion with a two-minute "elevator pitch" using a single slide (which must be submitted in advance). The session chair will select questions from both the live audience and questions collected through the chat interface in advance. Paper will be discussed in the order indicated on the schedule, but there also will be the opportunity to explore connections between different papers in the same session.
Timing:
All paper sessions will take place during the main conference, running from Wednesday, 5 May 2021 to Friday, 7 May 2021. Each session will be 75 minutes long. All times mentioned refer to the local time in London (British Summer Time, GMT+1).
Computational Social Choice 1 (Wednesday, 9am)
Session Chair: Jérôme Lang
- Computing the Extremal Possible Ranks with Incomplete Preferences
Aviram Imber and Benny Kimelfeld - Rankings for Bipartite Tournaments via Chain Editing
Joseph Singleton and Richard Booth - Complexity of Scheduling and Predicting Round-Robin Tournaments
Dorothea Baumeister and Tobias Alexander Hogrebe - Multivariate Analysis of Scheduling Fair Competitions
Siddharth Gupta and Meirav Zehavi - Multi-Robot Task Allocation—Complexity and Approximation
Haris Aziz, Hau Chan, Agnes Cseh, Bo Li, Fahimeh Ramezani and Chenhao Wang
[back to top]Computational Social Choice 2 (Wednesday, 4pm)
Session Chair: Reshef Meir
- Broadening the Research Agenda for Computational Social Choice: Multiple Preference Profiles and Multiple Solutions (Blue Sky Ideas Track)
Niclas Boehmer and Rolf Niedermeier - Group Fairness for Knapsack Problems
Deval Patel, Arindam Khan and Anand Louis - Complexity of Sequential Rules in Judgment Aggregation
Dorothea Baumeister, Linus Boes and Robin Weishaupt - Egalitarian Judgment Aggregation
Sirin Botan, Ronald de Haan, Marija Slavkovik and Zoi Terzopoulou - Aggregating Bipolar Opinions
Stefan Lauren, Francesco Belardinelli and Francesca Toni
[back to top]Computational Social Choice 3 (Thursday, 9am)
Session Chair: Dorothea Baumeister
- On the Indecisiveness of Kelly-Strategyproof Social Choice Functions
Felix Brandt, Martin Bullinger and Patrick Lederer - Manipulability of Thiele Methods on Party-List Profiles
Sirin Botan - Committee Selection using Attribute Approvals
Venkateswara Rao Kagita, Arun K Pujari, Vineet Padmanabhan, Haris Aziz and Vikas Kumar - Approval-Based Shortlisting
Martin Lackner and Jan Maly - Partition Aggregation for Participatory Budgeting
Pallavi Jain, Nimrod Talmon and Laurent Bulteau
[back to top]Computational Social Choice 4 (Thursday, 4pm)
Session Chair: Edith Elkind
- Strategyproof Facility Location Mechanisms on DiscreteTrees
Alina Filimonov and Reshef Meir - Probabilistic Inference of Winners in Elections by Independent Random Voters
Aviram Imber and Benny Kimelfeld - A Hotelling-Downs Framework for Party Nominees
Paul Harrenstein, Grzegorz Lisowski, Ramanujan Sridharan and Paolo Turrini - Classifying the Complexity of the Possible Winner Problem on Partial Chains
Vishal Chakraborty and Phokion Kolaitis - Predicting Voting Outcomes in Presence of Communities
Jacques Bara, Omer Lev and Paolo Turrini
[back to top]Computational Social Choice 5 (Friday, 9am)
Session Chair: Ronald de Haan
- Connections between Fairness Criteria and Efficiency for Allocating Indivisible Chores
Ankang Sun, Bo Chen and Xuan Vinh Doan - Fairness and Efficiency in Facility Location Problems with Continuous Demands
Chenhao Wang and Mengqi Zhang - Existence and Computation of Maximin Fair Allocations Under Matroid-Rank Valuations
Siddharth Barman and Paritosh Verma - Worst-case Bounds for Spending a Common Budget
Pierre Cardi, Laurent Gourvès and Julien Lesca - High-Multiplicity Fair Allocation Made More Practical
Robert Bredereck, Aleksander Figiel, Andrzej Kaczmarczyk, Dušan Knop and Rolf Niedermeier
[back to top]Game Theory 1 (Wednesday, 9am)
Session Chair: Tomasz Michalak
- A Game Theoretical Analysis of Non-Linear Blockchain System
Lin Chen, Lei Xu, Zhimin Gao, Ahmed Sunny, Keshav Kasichainula and Weidong Shi - Modeling Replicator Dynamics in Stochastic Games Using Markov Chain Method
Chuang Deng, Zhihai Rong, Lin Wang and Xiaofan Wang - Equilibrium Refinements for Multi-Agent Influence Diagrams: Theory and Practice
Lewis Hammond, James Fox, Tom Everitt, Alessandro Abate and Michael Wooldridge - Partial Robustness in Team Formation: Bridging the Gap between Robustness and Resilience
Nicolas Schwind, Emir Demirović, Katsumi Inoue and Jean Marie Lagniez - Rational Synthesis in the Commons with Careless and Careful Agents
Rodica Condurache, Catalin Dima, Youssouf Oualhadj and Nicolas Troquard
[back to top]Game Theory 2 (Wednesday, 4pm)
Session Chair: Valentin Robu
- Mechanism Design for Public Projects via Neural Networks
Guanhua Wang, Runqi Guo, Yuko Sakurai, Muhammad Ali Babar and Mingyu Guo - Siting and sizing of charging infrastructure for shared autonomous electric fleets
Ramin Ahadi, Wolfgang Ketter, John Collins and Nicolò Daina - Adversarial learning in revenue-maximizing auctions
Thomas Nedelec, Jules Baudet, Vianney Perchet and Noureddine El Karoui - The Price is (Probably) Right: Learning Market Equilibria from Samples
Omer Lev, Neel Patel, Vignesh Viswanathan and Yair Zick - Log-time Prediction Markets for Interval Securities
Miroslav Dudík, Xintong Wang, David Pennock and David Rothschild
[back to top]Game Theory 3 (Thursday, 9am)
Session Chair: Dengji Zhao
- An Autonomous Negotiating Agent Framework with Reinforcement Learning based Strategies and Adaptive Strategy Switching Mechanism
Ayan Sengupta, Yasser Mohammad and Shinji Nakadai - A Heuristic Algorithm for Multi-Agent Vehicle Routing with Automated Negotiation
Dave De Jonge, Filippo Bistaffa and Jordi Levy - Adaptive Operating Hours for Improved Performance of Taxi Fleets
Rajiv Ranjan Kumar, Pradeep Varakantham and Shih-Fen Cheng - Optimising Long-Term Outcomes using Real-World Fluent Objectives: An Application to Football
Ryan Beal, Georgios Chalkiadakis, Timothy Norman and Sarvapali Ramchurn - Walrasian Equilibria in Markets with Small Demands
Argyrios Deligkas, Themistoklis Melissourgos and Paul Spirakis
[back to top]Game Theory 4 (Thursday, 4pm)
Session Chair: Francisco C. Santos
- Evolution of Strategies in Sequential Security Games
Adam Żychowski and Jacek Mańdziuk - Reinforcement Learning for Unified Allocation and Patrolling in Signaling Games with Uncertainty
Aravind Venugopal, Elizabeth Bondi, Harshavardhan Kamarthi, Keval Dholakia, Balaraman Ravindran and Milind Tambe - Network Robustness via Global k-cores
Palash Dey, Suman Kalyan Maity, Sourav Medya and Arlei Silva - A Decentralised Self-Healing Approach for Network Topology Maintenance (JAAMAS Track)
Arles Rodriguez, Jonatan Gomez and Ada Diaconescu - Strategic Evasion of Centrality Measures
Marcin Waniek, Jan Woźnica, Kai Zhou, Yevgeniy Vorobeychik, Talal Rahwan and Tomasz Michalak
[back to top]Game Theory 5 (Friday, 9am)
Session Chair: Paolo Turrini
- Timely Information from Prediction Markets
Grant Schoenebeck, Chenkai Yu and Fang-Yi Yu - Mechanism Design Powered by Social Interactions (Blue Sky Ideas Track)
Dengji Zhao - Trader-Company Method: A Metaheuristic for Interpretable Stock Price Prediction
Katsuya Ito, Kentaro Minami, Kentaro Imajo and Kei Nakagawa - Sequential Mechanisms for Multi-type Resource Allocation
Sujoy Sikdar, Xiaoxi Guo, Haibin Wang, Lirong Xia and Yongzhi Cao - Mechanism Design for Housing Markets over Social Networks
Takehiro Kawasaki, Ryoji Wada, Taiki Todo and Makoto Yokoo
[back to top]Game Theory 6 (Friday, 4pm)
Session Chair: Tom Lenaerts
- Safe Pareto improvements for delegated game playing
Caspar Oesterheld and Vincent Conitzer - Tractable mechanisms for computing near-optimal utility functions
Rahul Chandan, Dario Paccagnan and Jason R. Marden - Nash Equilibria in Finite-Horizon Multiagent Concurrent Games
Senthil Rajasekaran and Moshe Vardi - Adaptive Cascade Submodular Maximization
Shaojie Tang and Jing Yuan - Feasible Coalition Sequences
Tabajara Krausburg, Jürgen Dix and Rafael H. Bordini
[back to top]Humans and AI 1 (Wednesday, 9am)
Session Chair: Catherine Pelachaud
- Reason Explanation for Encouraging Behaviour Change Intention
Amal Abdulrahman, Deborah Richards and Ayse Aysin Bilgin - Better Metrics for Evaluating Explainable Artificial Intelligence (Blue Sky Ideas Track)
Avi Rosenfeld - CMCF: An architecture for realtime gesture generation by Clustering gestures by Motion and Communicative Function
Carolyn Saund, Andrei Bîrlădeanu and Stacy Marsella - ELVIRA: an Explainable Agent for Value and Utility-driven Multiuser Privacy
Francesca Mosca and Jose M. Such - Extended Goal Recognition: a Planning-Based Model for Strategic Deception
Peta Masters, Michael Kirley and Wally Smith
[back to top]Agent Models and Theories 1 (Wednesday, 4pm)
Session Chair: Tim Norman
- A Novelty-Centric Agent Architecture for Changing Worlds
Faizan Muhammad, Vasanth Sarathy, Gyan Tatiya, Shivam Goel, Saurav Gyawali, Mateo Guaman, Jivko Sinapov and Matthias Scheutz - Grab the Reins of Crowds: Estimating the Effects of Crowd Movement Guidance Using Causal Inference
Koh Takeuchi, Ryo Nishida, Hisashi Kashima and Masaki Onishi - Accelerating Recursive Partition-Based Causal Structure Learning
Md. Musfiqur Rahman, Ayman Rasheed, Md. Mosaddek Khan, Mohammad Ali Javidian, Pooyan Jamshidi and Md. Mamun-Or-Rashid - Grid-to-Graph: Flexible Spatial Relational Inductive Biases for Reinforcement Learning
Zhengyao Jiang, Pasquale Minervini, Minqi Jiang and Tim Rocktäschel - Cognitive Homeostatic Agents (Blue Sky Ideas Track)
Amol Kelkar
[back to top]Engineering Multiagent Systems (Thursday, 9am)
Session Chair: Brian Logan
- Programming Agent-based Mobile Apps: The JaCa-Android Framework (JAAMAS Track)
Angelo Croatti and Alessandro Ricci - Active Perception Within BDI Agents Reasoning Cycle
Gustavo Silva, Jomi Hübner and Leandro Becker - Robustness based on Accountability in Multiagent Organizations
Matteo Baldoni, Cristina Baroglio, Roberto Micalizio and Stefano Tedeschi - User and System Stories: an agile approach for managing requirements in AOSE
Sebastian Rodriguez, John Thangarajah and Michael Winikoff - Summarising a Framework for the Certification of Reliable Autonomous Systems (JAAMAS Track)
Michael Fisher, Viviana Mascardi, Kristin Yvonne Rozier, Bernd-Holger Schlingloff, Michael Winikoff and Neil Yorke-Smith
[back to top]Agent Models and Theories 2 (Thursday, 4pm)
Session Chair: Terry Payne
- Probabilistic Control Argumentation Frameworks
Fabrice Gaignier, Yannis Dimopoulos, Jean-Guy Mailly and Pavlos Moraitis - On a Notion of Monotonic Support for Bipolar Argumentation Frameworks
Anis Gargouri, Sébastien Konieczny, Pierre Marquis and Srdjan Vesic - A General Trust Framework for Multi-Agent Systems
Mingxi Cheng, Chenzhong Yin, Junyao Zhang, Shahin Nazarian, Jyotirmoy Deshmukh and Paul Bogdan - Knowing Why -- On the Dynamics of Knowledge about Actual Causes in the Situation Calculus
Shakil Khan and Yves Lespérance - Constructing Junction Tree Agent Organization with Privacy (JAAMAS Track)
Yang Xiang and Abdulrahman Alshememry
[back to top]Agent Models and Theories 3 (Friday, 9am)
Session Chair: Neil Yorke-Smith
- Agent Programming in the Cognitive Era (JAAMAS Track)
Rafael Bordini, Amal El Fallah Seghrouchni, Koen Hindriks, Brian Logan and Alessandro Ricci - Multi-Agent Reinforcement Learning with Temporal Logic Specifications
Lewis Hammond, Alessandro Abate, Julian Gutierrez and Michael Wooldridge - Explaining BDI agent behaviour through dialogue
Louise Dennis and Nir Oren - Logic-based Technologies for Multi-agent Systems: Summary of a Systematic Literature Review (JAAMAS Track)
Roberta Calegari, Giovanni Ciatto, Viviana Mascardi and Andrea Omicini - Intention Progression using Quantitative Summary Information
Yuan Yao, Natasha Alechina, Brian Logan and John Thangarajah
[back to top]Formal Specification and Verification (Friday, 4pm)
Session Chair: Natasha Alechina
- Regular Model Checking Approach to Knowledge Reasoning over Parameterized Systems
Daniel Stan and Anthony Widjaja Lin - Logic-based Specification and Verification of Homogeneous Dynamic Multi-agent Systems (JAAMAS Track)
Riccardo De Masellis and Valentin Goranko - Mean-Payoff Games with Omega-Regular Specifications
Thomas Steeples, Julian Gutierrez and Michael Wooldridge - A Logic of Evaluation
Emiliano Lorini - Quantified Announcements and Common Knowledge
Rustam Galimullin and Thomas Ågotnes
[back to top]Agent-Based Modelling and Planning (Wednesday, 9am)
Session Chair: John Thangarajah
- An Agent-Based Model to Predict Pedestrians Trajectories with an Autonomous Vehicle in Shared Spaces
Manon Prédhumeau, Lyuba Mancheva, Julie Dugdale and Anne Spalanzani - Models we can Trust: Toward a Systematic Discipline of (Agent-Based) Model Interpretation and Validation (Blue Sky Ideas Track)
Gabriel Istrate - Moblot: Molecular Oblivious Robots
Serafino Cicerone, Alessia Di Fonso, Gabriele Di Stefano and Alfredo Navarra - Identification of unexpected decisions in Partially Observable Monte Carlo Planning: a rule-based approach
Giulio Mazzi, Alberto Castellini and Alessandro Farinelli - Beyond To Act or Not to Act: Fast Lagrangian Approaches to General Multi-Action Restless Bandits
Jackson Killian, Andrew Perrault and Milind Tambe
[back to top]Multiagent Planning and Scheduling 1 (Wednesday, 4pm)
Session Chair: Felipe Meneguzzi
- Risk-Aware Interventions in Public Health: Planning with Restless Multi-Armed Bandits
Aditya Mate, Andrew Perrault and Milind Tambe - A Norm Enforcement Mechanism for a Time-Constrained Conditional Normative Framework (JAAMAS Track)
Babatunde Akinkunmi and Florence Babalola - On Teammate-Pattern-Aware Autonomy (JAAMAS Track)
Edmund Durfee, Abhishek Thakur and Eli Goldweber - MAPFAST: A Deep Algorithm Selector for Multi Agent Path Finding using Shortest Path Embeddings
Jingyao Ren, Vikraman Sathiyanarayanan, Eric Ewing, Baskin Senbaslar and Nora Ayanian - Sequential Ski Rental Problem
Anant Shah and Arun Rajkumar
[back to top]Innovative Applications (Thursday, 9am)
Session Chair: Samarth Swarup
- Sparse training theory for scalable and efficient agents (Blue Sky Ideas Track)
Decebal Constantin Mocanu, Elena Mocanu, Tiago Pinto, Selima Curci, Phuong H. Nguyen, Madeleine Gibescu, Damien Ernst and Zita Vale - Autonomous Agents and Multiagent Systems Challenges in Earth Observation Satellite Constellations (Blue Sky Ideas Track)
Gauthier Picard, Clément Caron, Jean-Loup Farges, Jonathan Guerra, Cédric Pralet and Stéphanie Roussel - Multi-modal agents for business intelligence (Blue Sky Ideas Track)
Jeffrey Kephart - Peer-to-peer Autonomous Agent Communication Network
Lokman Rahmani, David Minarsch and Jonathan Ward - Responsibility Research for Trustworthy Autonomous Systems (Blue Sky Ideas Track)
Vahid Yazdanpanah, Enrico H. Gerding, Sebastian Stein, Mehdi Dastani, Catholijn M. Jonker and Timothy J. Norman
[back to top]Multiagent Planning and Scheduling 2 (Thursday, 4pm)
Session Chair: Ed Durfee
- A Local Search Based Approach to Solve Continuous DCOPs
Amit Sarker, Moumita Choudhury and Md. Mosaddek Khan - Latency-Aware Local Search for Distributed Constraint Optimization
Ben Rachmut, Roie Zivan and William Yeoh - Scalable Anytime Planning for Multi-Agent MDPs
Shushman Choudhury, Jayesh Gupta, Peter Morales and Mykel Kochenderfer - Learning Node-Selection Strategies in Bounded Suboptimal Conflict-Based Search for Multi-Agent Path Finding
Taoan Huang, Bistra Dilkina and Sven Koenig - Efficient Nonmyopic Online Allocation of Scarce Reusable Resources
Zehao Dong, Sanmay Das, Patrick Fowler and Chien-Ju Ho
[back to top]Values and Preferences (Friday, 9am)
Session Chair: Natalia Criado
- Value-Guided Synthesis of Parametric Normative Systems
Nieves Montes and Carles Sierra - Axies: Identifying and Evaluating Context-Specific Values
Enrico Liscio, Michiel van der Meer, Luciano Cavalcante Siebert, Catholijn M. Jonker, Niek Mouter and Pradeep K. Murukannaiah - A Knowledge Compilation Map for Conditional Preference Statements-based Languages
Helene Fargier and Jérôme Mengin - Efficient Exact Computation of Setwise Minimax Regret for Interactive Preference Elicitation
Federico Toffano, Paolo Viappiani and Nic Wilson - Achieving Sybil-proofness in Distributed Work Systems
Alexander Stannat, Can Umut Ileri, Dion Gijswijt and Johan Pouwelse
[back to top]Humans and AI 2 (Friday, 4pm)
Session Chair: Sandip Sen
- Efficiently Guiding Imitation Learning Agents with Human Gaze
Akanksha Saran, Ruohan Zhang, Elaine Schaertl Short and Scott Niekum - Decision Model for a Virtual Agent that can Touch and be Touched
Fabien Boucaud, Catherine Pelachaud and Indira Thouvenin - A Computational Model of Coping for simulating human behavior in high-stress situations
Nutchanon Yongsatianchot and Stacy Marsella - The Seeing-Eye Robot Grand Challenge: Rethinking Automated Care (Blue Sky Ideas Track)
Reuth Mirsky and Peter Stone - Towards Transferrable Personalized Student Models in Educational Games
Samuel Spaulding, Jocelyn Shen, Haewon Park and Cynthia Breazeal
[back to top]Multiagent Learning 1 (Wednesday, 9am)
Session Chair: Enda Howley
- Learning Correlated Communication Topology in Multi-Agent Reinforcement learning
Yali Du, Bo Liu, Vincent Moens, Ziqi Liu, Zhicheng Ren, Jun Wang, Xu Chen and Haifeng Zhang - Cooperative and Competitive Biases for Multi-Agent Reinforcement Learning
Heechang Ryu, Hayong Shin and Jinkyoo Park - Scalable Optimization for Wind Farm Control using Coordination Graphs
Timothy Verstraeten, Pieter-Jan Daems, Eugenio Bargiacchi, Diederik M. Roijers, Pieter Libin and Jan Helsen - Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning
Xueguang Lyu, Yuchen Xiao, Brett Daley and Christopher Amato - Modeling the Interaction between Agents in Cooperative Multi-Agent Reinforcement Learning
Xiaoteng Ma, Yiqin Yang, Chenghao Li, Qianchuan Zhao, Jun Yang and Yiwen Lu
[back to top]Multiagent Learning 2 (Wednesday, 4pm)
Session Chair: Patrick Mannion
- Reward Machines for Cooperative Multi-Agent Reinforcement Learning
Cyrus Neary, Zhe Xu, Bo Wu and Ufuk Topcu - Multi-Agent Coordination in Adversarial Environments through Signal Mediated Strategies
Federico Cacciamani, Andrea Celli, Marco Ciccone and Nicola Gatti - STRATA: Unified Framework for Task Assignments in Large Teams of Heterogeneous Agents (JAAMAS Track)
Harish Ravichandar, Kenneth Shaw and Sonia Chernova - Emergent Communication under Competition
Michael Noukhovitch, Travis LaCroix, Angeliki Lazaridou and Aaron Courville - Structured Diversification Emergence via Reinforced Organization Control and Hierachical Consensus Learning
Wenhao Li, Xiangfeng Wang, Bo Jin, Junjie Sheng, Yun Hua and Hongyuan Zha
[back to top]Multiagent Learning 3 (Thursday, 9am)
Session Chair: Viliam Lisý
- Environment Shift Games: Are Multiple Agents the Solution, and not the Problem, to Non-Stationarity? (Blue Sky Ideas Track)
Alexander Mey and Frans A. Oliehoek - Transferable Environment Poisoning: Training-time Attack on Reinforcement Learning
Hang Xu, Rundong Wang, Lev Raizman and Zinovi Rabinovich - Spatial Consensus-Prevention in Robotic Swarms
Saar Cohen and Noa Agmon - Cooperative Policy Learning with Pre-trained Heterogeneous Observation Representation
Wenlei Shi, Xinran Wei, Jia Zhang, Xiaoyuan Ni, Arthur Jiang, Jiang Bian and Tie-Yan Liu - Knowledge Improvement and Diversity under Interaction-Driven Adaptation of Learned Ontologies
Yasser Bourahla, Manuel Atencia and Jérôme Euzenat
[back to top]Multiagent Learning 4 (Thursday, 4pm)
Session Chair: Chris Amato
- Collaborative Multiagent Decision Making for Lane-Free Autonomous Driving
Dimitrios Troullinos, Georgios Chalkiadakis, Ioannis Papamichail and Markos Papageorgiou - Cooperative Prioritized Sweeping
Eugenio Bargiacchi, Timothy Verstraeten and Diederik M. Roijers - Scalable Multiagent Driving Policies For Reducing Traffic Congestion
Jiaxun Cui, William Macke, Harel Yedidsion, Aastha Goyal, Daniel Urieli and Peter Stone - Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning
Sheng Li, Jayesh K. Gupta, Peter Morales, Ross Allen and Mykel J. Kochenderfer - Multi-Agent Graph Attention Communication and Teaming
Yaru Niu, Rohan Paleja and Matthew Gombolay
[back to top]Multiagent Learning 5 (Friday, 9am)
Session Chair: Daan Bloembergen
- Accumulating Risk Capital Through Investing in Cooperation
Charlotte Roman, Michael Dennis, Andrew Critch and Stuart Russell - Loss Bounds for Approximate Influence-Based Abstraction
Elena Congeduti, Alexander Mey and Frans Oliehoek - Cooperation and Reputation Dynamics with Reinforcement Learning
Nicolas Anastassacos, Julian Garcia, Stephen Hailes and Mirco Musolesi - Improved Cooperation by Exploiting a Common Signal
Panayiotis Danassis, Zeki Doruk Erden and Boi Faltings - Cooperation between Independent Reinforcement Learners under Wealth Inequality and Collective Risks
Ramona Merhej, Fernando P. Santos, Francisco S. Melo and Francisco C. Santos
[back to top]Multiagent Learning 6 (Friday, 4pm)
Session Chair: Fernando Santos
- Safe Multi-Agent Reinforcement Learning via Shielding
Ingy Elsayed-Aly, Suda Bharadwaj, Christopher Amato, Rüdiger Ehlers, Ufuk Topcu and Lu Feng - Off-Policy Exploitability-Evaluation in Two-Player Zero-Sum Markov Games
Kenshi Abe and Yusuke Kaneko - Cooperative-Competitive Reinforcement Learning with History-Dependent Rewards
Keyang He, Bikramjit Banerjee and Prashant Doshi - An Abstraction-based Method to Check Multi-Agent Deep Reinforcement-Learning Behaviors
Pierre El Mqirmi, Francesco Belardinelli and Borja G. León - Partially Observable Mean Field Reinforcement Learning
Sriram Ganapathi Subramanian, Matthew Taylor, Mark Crowley and Pascal Poupart
[back to top]Reinforcement Learning 1 (Wednesday, 9am)
Session Chair: Decebal Mocanu
- Show Me the Way: Intrinsic Motivation from Demonstrations
Leonard Hussenot, Robert Dadashi, Matthieu Geist and Olivier Pietquin - Exploration of Indoor Environments through Predicting the Layout of Partially Observed Rooms
Matteo Luperto, Luca Fochetta and Francesco Amigoni - Learning Complex Policy Distribution with CEM Guided Adversarial Hypernetwork
Shi Yuan Tang, Athirai A. Irissappane, Frans A. Oliehoek and Jie Zhang - State-Aware Variational Thompson Sampling for Deep Q-Networks
Siddharth Aravindan and Wee Sun Lee - AlwaysSafe: Reinforcement Learning without Safety Constraint Violations during Training
Thiago D. Simão, Nils Jansen and Matthijs T. J. Spaan
[back to top]Reinforcement Learning 2 (Wednesday, 4pm)
Session Chair: Bo An
- Drone Formation Control via Belief-Correlated Imitation Learning
Bo Yang, Chaofan Ma and Xiaofang Xia - Self-Imitation Advantage Learning
Johan Ferret, Olivier Pietquin and Matthieu Geist - Action Priors for Large Action Spaces in Robotics
Ondrej Biza, Dian Wang, Robert Platt, Jan-Willem van de Meent and Lawson L.S. Wong - Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems (Blue Sky Ideas Track)
Yaodong Yang, Matthew E. Taylor, Jun Luo, Ying Wen, Oliver Slumbers, Daniel Graves, Haitham Bou Ammar and Jun Wang - Guiding Evolutionary Strategies with Off-Policy Actor-Critic
Yunhao Tang
[back to top]Reinforcement Learning 3 (Thursday, 9am)
Session Chair: Elena Mocanu
- Cyber Attack Intent Recognition and Active Deception using Factored Interactive POMDPs
Aditya Shinde, Prashant Doshi and Omid Setayeshfar - To hold or not to hold? - Reducing Passenger Missed Connections in Airlines using Reinforcement Learning
Tejasvi Malladi, Karpagam Murugappan, Depak Sudarsanam, Ramasubramanian Suriyanarayanan and Arunchandar Vasan - Temporal Watermarks for Deep Reinforcement Learning Models
Kangjie Chen, Shangwei Guo, Tianwei Zhang, Shuxin Li and Yang Liu - Deceptive Reinforcement Learning for Privacy-Preserving Planning
Zhengshang Liu, Yue Yang, Tim Miller and Peta Masters - Parallel Curriculum Experience Replay in Distributed Reinforcement Learning
Yuyu Li and Jianmin Ji
[back to top]Reinforcement Learning 4 (Thursday, 4pm)
Session Chair: Gabriel Ramos
- Interrogating the Black Box: Transparency through Information-Seeking Dialogues
Andrea Aler Tubella, Andreas Theodorou and Juan Carlos Nieves - Active Screening for Recurrent Diseases: A Reinforcement Learning Approach
Han Ching Ou, Haipeng Chen, Shahin Jabbari and Milind Tambe - Multiagent Epidemiologic Inference through Realtime Contact Tracing
Guni Sharon, James Ault, Peter Stone, Varun Kompella and Roberto Capobianco - No More Hand-Tuning Rewards: Masked Constrained Policy Optimization for Safe Reinforcement Learning
Stef Van Havermaet, Yara Khaluf and Pieter Simoens - Let the DOCTOR Decide Whom to Test: Adaptive Testing Strategies to Tackle the COVID-19 Pandemic
Yu Liang and Amulya Yadav
[back to top]Reinforcement Learning 5 (Friday, 9am)
Session Chair: Jivko Sinapov
- Teaching a robot with unlabeled instructions: The TICS architecture (JAAMAS Track)
Anis Najar, Olivier Sigaud and Mohamed Chetouani - Action Advising with Advice Imitation in Deep Reinforcement Learning
Ercument Ilhan, Jeremy Gow and Diego Perez Liebana - Facial Feedback for Reinforcement Learning: A Case Study and Offline Analysis Using the TAMER Framework (JAAMAS Track)
Guangliang Li, Hamdi Dibeklioglu, Shimon Whiteson and Hayley Hung - Energy Based Imitation Learning
Minghuan Liu, Tairan He, Minkai Xu and Weinan Zhang - Imitation Learning from Pixel-Level Demonstrations by HashReward
Xin-Qiang Cai, Yao-Xiang Ding, Yuan Jiang and Zhi-Hua Zhou
[back to top]Reinforcement Learning 6 (Friday, 4pm)
Session Chair: Haipeng Chen
- TDprop: Does Adaptive Optimization With Jacobi Preconditioning Help Temporal Difference Learning?
Joshua Romoff, Peter Henderson, David Kanaa, Emmanuel Bengio, Ahmed Touati, Pierre-Luc Bacon and Joelle Pineau - Minimum-delay Adaptation in Non-Stationary Reinforcement Learning via Online High-Confidence Change-Point Detection
Lucas N. Alegre, Ana L. C. Bazzan and Bruno C. da Silva - SEERL : Sample Efficient Ensemble Reinforcement Learning
Rohan Saphal, Balaraman Ravindran, Dheevatsa Mudigere, Sasikanth Avancha and Bharat Kaul - Action Selection For Composable Modular Deep Reinforcement Learning
Vaibhav Gupta, Daksh Anand, Praveen Paruchuri and Akshat Kumar - SPOTTER: Extending Symbolic Planning Operators through Targeted Reinforcement Learning
Vasanth Sarathy, Daniel Kasenberg, Shivam Goel, Jivko Sinapov and Matthias Scheutz
[back to top]