AAMAS

3,205 papers925 directions
The International Conference on Autonomous Agents and Multiagent Systems (AAMAS) is a research venue focused on the study of autonomous agents and their interactions within multiagent environments. Active since 2002, the venue has published over 3,500 papers covering the design, modeling, and evaluation of intelligent systems. It serves as a forum for research that combines artificial intelligence, distributed systems, and game theory to address complex coordination and decision-making problems. Research at AAMAS frequently explores multi-agent reinforcement learning (MARL), with a focus on centralized training with decentralized execution, value decomposition for cooperative tasks, and learning in non-stationary environments. The venue also features significant work in algorithmic game theory and social choice, including the fair allocation of indivisible items, coalition structure generation, and social welfare maximization under uncertainty. Other prominent topics include multi-agent path finding, logic-guided reward shaping, and the development of offline meta-reinforcement learning policies. The venue’s contributors include researchers such as Milind Tambe, Michael J. Wooldridge, Sarit Kraus, and Peter Stone. Published works often address practical challenges in multiagent systems, such as participation incentives in cooperative games, safety-inferred imitation policies, and scalable search algorithms. By integrating learning techniques with formal logic and economic principles, AAMAS facilitates the development of agents capable of operating in episodic markets, stochastic environments, and complex visual question-answering benchmarks.

Papers by Year

2026 8
2025 220
2024 257
2023 277
2022 186
2021 149
2020 199
2019 200
2018 168
2017 135
2016 136
2015 168
2014 167
2013 134
2012 134
2011 110
2010 110
2009 86
2008 59
2007 86
2006 73
2005 55
2004 62
2003 45
2002 50

Top Research Directions

Research directions most represented by papers from this venue.

Sample Efficient Reinforcement Learning 26
The Moving Target Problem in Multi Agent Learning 22
The Empirical Validation Gap 21
Centralized Training with Decentralized Execution 20
The Zero-Sum Restriction in Multi-Agent Learning 18
Decentralized Coordination Under Partial Observability 18
Strategyproof Resource Allocation Without Money 17
Credit Assignment in Cooperative Multi-Agent Systems 15
Scaling Multi-Agent Reinforcement Learning via Structural Approximations 13
Proving Computational Intractability Through Hardness Reductions 12
Safe Reinforcement Learning via Constrained Markov Decision Processes 12
Exploration Strategies for Sparse Reward Reinforcement Learning 12
Aligning Selfish Routing with Socially Optimal Traffic Flow 11
Computational Complexity as a Barrier to Election Manipulation 11
Taming the Complexity of Decentralized Multiagent Planning 11

Top Authors

AuthorPapers
Milind Tambe131
Michael J. Wooldridge95
Sarit Kraus76
Peter Stone69
Juan Antonio Rodriguez Aguilar44
Katia P. Sycara41
Mehdi Dastani41
Alessio Lomuscio40
Tuomas Sandholm40
Sven Koenig37
Matthew E. Taylor35
Bo An33
Pradeep Varakantham32
Michael P. Wellman31
William Yeoh31
Vincent Conitzer30
Alessandro Farinelli29
Ana L. C. Bazzan29
Chunyan Miao29
Haris Aziz29

Impactful Papers

Papers from this venue that shaped research clusters.

Foundational

Influential

Related Venues

Venues with the most similar research cluster distributions.

Papers

TitleYear
An extensive model checking framework for multi-agent systems2014
An interactive approach for situated task specification through verbal instructions2014
An interactive virtual audience platform for public speaking training2014
A normative agent-based model for predicting smoking cessation trends2014
A note on the undercut procedure2014
A novel ex-post truthful mechanism for multi-slot sponsored search auctions2014
Anytime coalition structure generation on synergy graphs2014
A pheromone-based traffic management model for vehicle re-routing and traffic light control2014
A POMDP based approach to optimally select sellers in electronic marketplaces2014
Applied robotics: precision placement in RoboCup@Work2014
Approximating the shapley value via multi-issue decompositions2014
A practical robustness measure of incentive mechanisms2014
A quality assuring multi-armed bandit crowdsourcing mechanism with incentive compatible learning2014
A quantitative analysis of decision process in social groups using human trajectories2014
Argumentation-based reinforcement learning for robocup soccer takeaway2014
ASP-DPOP: solving distributed constraint optimization problems with logic programming2014
Assessing learned models of fish schooling behavior2014
Asymmetric abstractions for adversarial settings2014
A testbed for autonomous robot surveillance2014
A testbed to evaluate the robustness of reputation systems in e-marketplaces2014
AtomicOrchid: human-agent collectives to the rescue2014
Auctioning a cake: truthful auctions of heterogeneous divisible goods2014
Automated agents' behavior in the trust-revenge game incomparison to other cultures2014
Automatic rule identification for agent-based crowd models through gene expression programming2014
Boosted and reward-regularized classification for apprenticeship learning2014
Bootstrap statistics for empirical games2014
Bribery in multiple-adversary path-disruption games is hard for the second level of the polynomial hierarchy2014
BudgetFix: budget limited crowdsourcing for interdependent task allocation with quality guarantees2014
Building THINC: user incentivization and meeting rescheduling for energy savings2014
Characterizing online cost-sharing mechanisms fordemand responsive transport systems2014
CLEANing the reward: counterfactual actions to remove exploratory action noise in multiagent learning (extended abstract)2014
Cloud service selection based on contextual subjective assessment and objective assessment2014
Collective action through common knowledge using a facebook model2014
Collective decision making in distributed systems inspired by honeybees behaviour2014
Combinatorial auctions without money2014
Comparison and validation of synthetic social contact networks for epidemic modeling2014
Complexity of manipulation, bribery, and campaign management in bucklin and fallback voting2014
Complexity of stability-based solution concepts in multi-issue and MC-net cooperative games2014
Computational epidemiology as a challenge domain for multiagent systems2014
Conservative collision prediction and avoidance for stochastic trajectories in continuous time and space2014
Constrained scheduling of robot exploration tasks2014
Controlling elections with bounded single-peaked width2014
Convex coverage set methods for multi-objective collaborative decision making2014
Cooperative max games and agent failures2014
Cooperative weakest link games2014
Correlated multi-dimensional qos metrics for trust evaluation within web services2014
Cost optimal planning with LP-based multi-valued landmark heuristic2014
Decision-theoretic approach to maximizing fairness in multi-target observation in multi-camera surveillance2014
Declarative-procedural memory interaction in learning agents2014
Dialogical two-agent decision making with assumption-based argumentation2014

« prev Page 42/65 next »