AAMAS 2020

199 papers
The 2020 edition of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS) featured 251 papers, with a strong emphasis on reinforcement learning and transferability. A recurring theme was the development of methods to mitigate negative transfer in lifelong learning, utilizing adaptive policy reuse, structural mapping, and formal metrics for task relatedness. Research also addressed exploration challenges, focusing on diversity maintenance for evolutionary search and mitigating entropy collapse in reasoning models. The conference also highlighted advancements in computational game theory and market design. Studies examined the computational limits of constrained matching markets, such as internship allocation, and analyzed Bayesian Nash Equilibrium in discrete auctions. Practical applications of multi-agent systems were well-represented, including research on large-scale warehouse pathfinding and disaster evacuation strategies. Prolific authors for the year included Alessandro Farinelli, Milind Tambe, and David C. Parkes. These contributions collectively advanced the understanding of how agents adapt to new tasks and operate within complex, resource-constrained environments.

Top Research Directions

Research directions most represented by AAMAS 2020 papers.

Sample Efficient Reinforcement Learning 7
Centralized Training with Decentralized Execution 5
Proving Computational Intractability Through Hardness Reductions 5
Strategyproof Resource Allocation Without Money 4
The Zero-Sum Restriction in Multi-Agent Learning 4
The Empirical Validation Gap 4
Greedy Maximization for Submodular Subset Selection 3
Preventing Entropy Collapse in Reinforcement Learning 3
Aligning Selfish Routing with Socially Optimal Traffic Flow 3
Overcoming Fundamental Impossibilities in Mechanism Design 3
Computational Complexity as a Barrier to Election Manipulation 3
Hierarchical Reinforcement Learning for Complex Task Decomposition 3
Safe Reinforcement Learning via Constrained Markov Decision Processes 3
Reinforcement Learning in Partially Observable Environments 3
Credit Assignment in Cooperative Multi-Agent Systems 3

Top Authors

AuthorPapers
Alessandro Farinelli4
Anil Vullikanti3
Ann Nowe3
David C. Parkes3
Diederik M Roijers3
Doina Precup3
Edith Elkind3
Joel Z Leibo3
Milind Tambe3
Pingzhong Tang3
Sarit Kraus3
William Yeoh3
Alessio Lomuscio2
Alex Pentland2
Amos Azaria2
Ana-Andreea Stoica2
Andrei Lupu2
Andrew Perrault2
Bruno Lacerda2
Changjie Fan2

Impactful Papers

Papers from AAMAS 2020 that shaped research clusters.

Foundational

Influential

Papers

Title
Likelihood Quantile Networks for Coordinating Multi-Agent Reinforcement Learning
Limitations of Greed: Influence Maximization in Undirected Networks Re-visited
Limiting the Deviation Incentives in Resource Sharing Networks
Long-Run Multi-Robot Planning With Uncertain Task Durations
Manipulating Node Similarity Measures in Networks
Mastering Basketball With Deep Reinforcement Learning: An Integrated Curriculum Training Approach
Matching Affinity Clustering: Improved Hierarchical Clustering at Scale with Guarantees
Maximizing Information Gain in Partially Observable Environments via Prediction Rewards
Mechanism Design for Defense Coordination in Security Games
META-Learning State-based Eligibility Traces for More Sample-Efficient Policy Evaluation
MGpi: A Computational Model of Multiagent Group Perception and Interaction
Minimizing Margin of Victory for Fair Political and Educational Districting
Mitigating the Negative Side Effects of Reasoning with Imperfect Models: A Multi-Objective Approach
Modeling Disinformation and the Effort to Counter It: A Cautionary Tale of When the Treatment Can Be Worse Than the Disease
Modified Actor-Critics
Multi-agent Adversarial Inverse Reinforcement Learning with Latent Variables
Multimodal Representation Learning for Robotic Cross-Modality Policy Transfer
Multi-Path Policy Optimization
Multiple Levels of Importance in Matching with Distributional Constraints: Extended Abstract
Multi-Robot Planning Under Uncertainty with Congestion-Aware Models
Multi Type Mean Field Reinforcement Learning
Multiwinner Candidacy Games
Networked Multi-Agent Reinforcement Learning with Emergent Communication
Neural MMO v1.3: A Massively Multiagent Game Environment for Training and Evaluating Neural Networks
Neural Replicator Dynamics: Multiagent Learning via Hedging Policy Gradients
New Algorithms for Continuous Distributed Constraint Optimization Problems
Non-Uniform Policies for Multi-Robot Asymmetric Perimeter Patrol in Adversarial Domains
Normalizing Flow Model for Policy Representation in Continuous Action Multi-agent Systems
Objective Social Choice: Using Auxiliary Information to Improve Voting Outcomes
Off-Policy Deep Reinforcement Learning with Analogous Disentangled Exploration
On Algorithmic Decision Procedures in Emergency Response Systems in Smart and Connected Communities
On Emergent Communication in Competitive Multi-Agent Teams
On-line Estimators for Ad-hoc Task Allocation
On the Complexity of Sequential Posted Pricing
Opponent Modelling for Reinforcement Learning in Multi-Objective Normal Form Games
Optimal Control in Partially Observable Complex Social Systems
Optimising Game Tactics for Football
Optimized Cost per Mille in Feeds Advertising
Option-Critic in Cooperative Multi-agent Systems
PANDA: Privacy-Aware Double Auction for Divisible Resources without a Mediator
Parameterised Verification of Strategic Properties in Probabilistic Multi-Agent Systems
Parameterized Complexity of Shift Bribery in Iterative Elections
Penalty Bidding Mechanisms for Allocating Resources and Overcoming Present-Bias
Plannable Approximations to MDP Homomorphisms: Equivariance under Actions
Playing Games in the Dark: An Approach for Cross-Modality Transfer in Reinforcement Learning
Policy-Gradient Algorithms Have No Guarantees of Convergence in Linear Quadratic Games
Policy Synthesis for Factored MDPs with Graph Temporal Logic Specifications
Privacy-Preserving Dark Pools
Private and Byzantine-Proof Cooperative Decision-Making
Real-time Learning and Planning in Environments with Swarms: A Hierarchical and a Parameter-based Simulation Approach

« prev Page 3/4 next »