{"total":174,"rows":[{"id":"2212.07489","title":"SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning","created":"2022-12-14","cited_by_count":122,"area":null},{"id":"2105.12196","title":"From Motor Control to Team Play in Simulated Humanoid Football","created":"2021-05-25","cited_by_count":87,"area":null},{"id":"2209.10342","title":"Partially Observable Markov Decision Processes in Robotics: A Survey","created":"2022-09-21","cited_by_count":86,"area":null},{"id":"2108.11887","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","created":"2021-08-26","cited_by_count":81,"area":null},{"id":"2304.09870","title":"Heterogeneous-Agent Reinforcement Learning","created":"2023-04-19","cited_by_count":69,"area":null},{"id":"2207.03530","title":"VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning","created":"2022-07-07","cited_by_count":68,"area":null},{"id":"2311.10090","title":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","created":"2023-11-16","cited_by_count":63,"area":null},{"id":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60,"area":null},{"id":"2111.09189","title":"ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind","created":"2021-10-15","cited_by_count":58,"area":null},{"id":"2409.03052","title":"An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning","created":"2024-09-04","cited_by_count":50,"area":null},{"id":"2111.11032","title":"Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Exploration","created":"2021-11-22","cited_by_count":49,"area":null},{"id":"2106.15691","title":"Deep Multiagent Reinforcement Learning: Challenges and Directions","created":"2021-06-29","cited_by_count":42,"area":null},{"id":"2110.05682","title":"Provably Efficient Reinforcement Learning in Decentralized General-Sum Markov Games","created":"2021-10-12","cited_by_count":42,"area":null},{"id":"2603.04370","title":"$\\tau$-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge","created":"2026-03-04","cited_by_count":39,"area":null},{"id":"2106.00285","title":"Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning","created":"2021-06-01","cited_by_count":38,"area":null},{"id":"2301.07137","title":"Heterogeneous Multi-Robot Reinforcement Learning","created":"2023-01-17","cited_by_count":36,"area":null},{"id":"2110.13484","title":"Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey","created":"2021-10-26","cited_by_count":34,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2207.07166","title":"K-level Reasoning for Zero-Shot Coordination in Hanabi","created":"2022-07-14","cited_by_count":32,"area":null},{"id":"2305.20076","title":"Decision-Oriented Dialogue for Human-AI Collaboration","created":"2023-05-31","cited_by_count":29,"area":null},{"id":"2310.01207","title":"Learn to Follow: Decentralized Lifelong Multi-agent Pathfinding via Planning and Learning","created":"2023-10-02","cited_by_count":29,"area":null},{"id":"2306.06924","title":"TASRA: a Taxonomy and Analysis of Societal-Scale Risks from AI","created":"2023-06-12","cited_by_count":26,"area":null},{"id":"2302.06205","title":"Order Matters: Agent-by-agent Policy Optimization","created":"2023-02-13","cited_by_count":24,"area":null},{"id":"2310.05208","title":"ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination","created":"2023-10-08","cited_by_count":24,"area":null},{"id":"2212.02705","title":"What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning?","created":"2022-12-06","cited_by_count":22,"area":null},{"id":"2108.01828","title":"Emergent Discrete Communication in Semantic Spaces","created":"2021-08-04","cited_by_count":20,"area":null},{"id":"2302.07515","title":"TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play","created":"2023-02-15","cited_by_count":20,"area":null},{"id":"2103.08067","title":"Quasi-Equivalence Discovery for Zero-Shot Emergent Communication","created":"2021-03-14","cited_by_count":19,"area":null},{"id":"2207.14138","title":"Generating Teammates for Training Robust Ad Hoc Teamwork Agents via Best-Response Diversity","created":"2022-07-28","cited_by_count":17,"area":null},{"id":"2111.06721","title":"Causal Multi-Agent Reinforcement Learning: Review and Open Problems","created":"2021-11-12","cited_by_count":16,"area":null},{"id":"2207.05219","title":"Grounding Aleatoric Uncertainty for Unsupervised Environment Design","created":"2022-07-11","cited_by_count":16,"area":null},{"id":"2101.04237","title":"Solving Common-Payoff Games with Approximate Policy Iteration","created":"2021-01-11","cited_by_count":15,"area":null},{"id":"2209.03859","title":"A Survey on Large-Population Systems and Scalable Multi-Agent Reinforcement Learning","created":"2022-09-08","cited_by_count":14,"area":null},{"id":"2305.02128","title":"System Neural Diversity: Measuring Behavioral Heterogeneity in Multi-Agent Learning","created":"2023-05-03","cited_by_count":14,"area":null},{"id":"2107.06434","title":"Centralized Model and Exploration Policy for Multi-Agent RL","created":"2021-07-14","cited_by_count":12,"area":null},{"id":"2202.05793","title":"Answer Set Planning: A Survey","created":"2022-02-11","cited_by_count":12,"area":null},{"id":"2203.04735","title":"A Survey on Reinforcement Learning Methods in Character Animation","created":"2022-03-07","cited_by_count":12,"area":null},{"id":"2205.01423","title":"Autonomy and Intelligence in the Computing Continuum: Challenges, Enablers, and Future Directions for Orchestration","created":"2022-05-03","cited_by_count":12,"area":null},{"id":"2211.08371","title":"Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches","created":"2022-11-15","cited_by_count":12,"area":null},{"id":"2304.14656","title":"From Explicit Communication to Tacit Cooperation:A Novel Paradigm for Cooperative MARL","created":"2023-04-28","cited_by_count":11,"area":null},{"id":"2307.11432","title":"An Analysis of Multi-Agent Reinforcement Learning for Decentralized Inventory Control Systems","created":"2023-07-21","cited_by_count":11,"area":null},{"id":"2405.15054","title":"Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning","created":"2024-05-23","cited_by_count":11,"area":null},{"id":"2110.06829","title":"Towards a fully RL-based Market Simulator","created":"2021-10-13","cited_by_count":10,"area":null},{"id":"2308.10284","title":"Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In the Game of Hanabi","created":"2023-08-20","cited_by_count":10,"area":null},{"id":"2212.01619","title":"DACOM: Learning Delay-Aware Communication for Multi-Agent Reinforcement Learning","created":"2022-12-03","cited_by_count":9,"area":null},{"id":"2110.12603","title":"Common Information based Approximate State Representations in Multi-Agent Reinforcement Learning","created":"2021-10-25","cited_by_count":8,"area":null},{"id":"2204.00302","title":"Actual Causality and Responsibility Attribution in Decentralized Partially Observable Markov Decision Processes","created":"2022-04-01","cited_by_count":8,"area":null},{"id":"2210.14640","title":"HSVI can solve zero-sum Partially Observable Stochastic Games","created":"2022-10-26","cited_by_count":8,"area":null},{"id":"2202.10881","title":"Coordinate-Aligned Multi-Camera Collaboration for Active Multi-Object Tracking","created":"2022-02-22","cited_by_count":7,"area":null},{"id":"2203.08015","title":"On-the-fly Strategy Adaptation for ad-hoc Agent Coordination","created":"2022-03-08","cited_by_count":7,"area":null},{"id":"2306.06136","title":"Robustness Testing for Multi-Agent Reinforcement Learning: State Perturbations on Critical Agents","created":"2023-06-09","cited_by_count":7,"area":null},{"id":"2307.06175","title":"Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior","created":"2023-07-12","cited_by_count":7,"area":null},{"id":"2310.15288","title":"Active teacher selection for reward learning","created":"2023-10-23","cited_by_count":7,"area":null},{"id":"2211.15824","title":"CLAS: Coordinating Multi-Robot Manipulation with Central Latent Action Spaces","created":"2022-11-28","cited_by_count":6,"area":null},{"id":"2405.14173","title":"Human-Agent Cooperation in Games under Incomplete Information through Natural Language Communication","created":"2024-05-23","cited_by_count":6,"area":null},{"id":"2406.06823","title":"Locally Interdependent Multi-Agent MDP: Theoretical Framework for Decentralized Agents with Dynamic Dependencies","created":"2024-06-10","cited_by_count":6,"area":null},{"id":"2505.23686","title":"ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamwork","created":"2025-05-29","cited_by_count":6,"area":null},{"id":"2106.00543","title":"MARL with General Utilities via Decentralized Shadow Reward Actor-Critic","created":"2021-05-29","cited_by_count":5,"area":null},{"id":"2110.07392","title":"Provably Efficient Multi-Agent Reinforcement Learning with Fully Decentralized Communication","created":"2021-10-14","cited_by_count":5,"area":null},{"id":"2301.05753","title":"Fairness and Sequential Decision Making: Limits, Lessons, and Opportunities","created":"2023-01-13","cited_by_count":5,"area":null},{"id":"2401.12455","title":"Multi-agent deep reinforcement learning with centralized training and decentralized execution for transportation infrastructure management","created":"2024-01-23","cited_by_count":5,"area":null},{"id":"2401.16444","title":"Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gain","created":"2024-01-28","cited_by_count":5,"area":null},{"id":"2411.17749","title":"The Partially Observable Off-Switch Game","created":"2024-11-25","cited_by_count":5,"area":null},{"id":"2109.08755","title":"Solving infinite-horizon Dec-POMDPs using Finite State Controllers within JESP","created":"2021-09-17","cited_by_count":4,"area":null},{"id":"2212.02075","title":"Differentiated Federated Reinforcement Learning Based Traffic Offloading on Space-Air-Ground Integrated Networks","created":"2022-12-05","cited_by_count":4,"area":null},{"id":"2302.03429","title":"Towards Skilled Population Curriculum for Multi-Agent Reinforcement Learning","created":"2023-02-07","cited_by_count":4,"area":null},{"id":"2303.09032","title":"Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learning","created":"2023-03-16","cited_by_count":4,"area":null},{"id":"2303.10665","title":"Major-Minor Mean Field Multi-Agent Reinforcement Learning","created":"2023-03-19","cited_by_count":4,"area":null},{"id":"2311.01953","title":"Optimistic Multi-Agent Policy Gradient","created":"2023-11-03","cited_by_count":4,"area":null},{"id":"2412.16244","title":"The impact of behavioral diversity in multi-agent reinforcement learning","created":"2024-12-19","cited_by_count":4,"area":null},{"id":"2412.17797","title":"Observation Interference in Partially Observable Assistance Games","created":"2024-12-23","cited_by_count":4,"area":null},{"id":"2506.11285","title":"Shapley Machine: A Game-Theoretic Framework for N-Agent Ad Hoc Teamwork","created":"2025-06-12","cited_by_count":4,"area":null},{"id":"2110.02736","title":"A Deep Reinforcement Learning Framework for Contention-Based Spectrum Sharing","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2301.04299","title":"SoK: Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning","created":"2023-01-11","cited_by_count":3,"area":null},{"id":"2302.12676","title":"Towards Computationally Efficient Responsibility Attribution in Decentralized Partially Observable MDPs","created":"2023-02-24","cited_by_count":3,"area":null},{"id":"2305.08481","title":"Task-Oriented Communication Design at Scale","created":"2023-05-15","cited_by_count":3,"area":null},{"id":"2408.07098","title":"QTypeMix: Enhancing Multi-Agent Cooperative Strategies through Heterogeneous and Homogeneous Value Decomposition","created":"2024-08-12","cited_by_count":3,"area":null},{"id":"2408.07644","title":"SigmaRL: A Sample-Efficient and Generalizable Multi-Agent Reinforcement Learning Framework for Motion Planning","created":"2024-08-14","cited_by_count":3,"area":null},{"id":"2508.06836","title":"Multi-level Advantage Credit Assignment for Cooperative Multi-Agent Reinforcement Learning","created":"2025-08-09","cited_by_count":3,"area":null},{"id":"2511.19726","title":"An Adaptive, Data-Integrated Agent-Based Modeling Framework for Explainable and Contestable Policy Design","created":"2025-11-24","cited_by_count":3,"area":null},{"id":"2107.00284","title":"SA-MATD3:Self-attention-based multi-agent continuous control method in cooperative environments","created":"2021-07-01","cited_by_count":2,"area":null},{"id":"2111.03431","title":"Learning to Cooperate with Unseen Agent via Meta-Reinforcement Learning","created":"2021-11-05","cited_by_count":2,"area":null},{"id":"2211.14426","title":"A Critical Review of Traffic Signal Control and A Novel Unified View of Reinforcement Learning and Model Predictive Control Approaches for Adaptive Traffic Signal Control","created":"2022-11-26","cited_by_count":2,"area":null},{"id":"2302.04218","title":"On the Computational Complexity of Ethics: Moral Tractability for Minds and Machines","created":"2023-02-08","cited_by_count":2,"area":null},{"id":"2305.15596","title":"Distributed Online Rollout for Multivehicle Routing in Unmapped Environments","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2307.08794","title":"Non-Stationary Policy Learning for Multi-Timescale Multi-Agent Reinforcement Learning","created":"2023-07-17","cited_by_count":2,"area":null},{"id":"2402.02954","title":"Solving Hierarchical Information-Sharing Dec-POMDPs: An Extensive-Form Game Approach","created":"2024-02-05","cited_by_count":2,"area":null},{"id":"2404.15583","title":"Multi-Agent Reinforcement Learning for Energy Networks: Computational Challenges, Progress and Open Problems","created":"2024-04-24","cited_by_count":2,"area":null},{"id":"2408.13139","title":"Optimally Solving Simultaneous-Move Dec-POMDPs: The Sequential Central Planning Approach","created":"2024-08-23","cited_by_count":2,"area":null},{"id":"2408.13750","title":"Multi-Agent Target Assignment and Path Finding for Intelligent Warehouse: A Cooperative Multi-Agent Deep Reinforcement Learning Perspective","created":"2024-08-25","cited_by_count":2,"area":null},{"id":"2502.17643","title":"Socratic: Enhancing Human Teamwork via AI-enabled Coaching","created":"2025-02-24","cited_by_count":2,"area":null},{"id":"2503.11726","title":"SPECTra: Scalable Multi-Agent Reinforcement Learning with Permutation-Free Networks","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2509.25550","title":"Unifying Agent Interaction and World Information for Multi-agent Coordination","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2512.20688","title":"Mechanism-Based Intelligence (MBI): Differentiable Incentives for Rational Coordination and Guaranteed Alignment in Multi-Agent Systems","created":"2025-12-22","cited_by_count":2,"area":null},{"id":"2602.17009","title":"Action-Graph Policies: Learning Action Co-dependencies in Multi-Agent Reinforcement Learning","created":"2026-02-19","cited_by_count":2,"area":null},{"id":"2602.20804","title":"Probing Dec-POMDP Reasoning in Cooperative MARL","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2107.08834","title":"A Multi-UAV System for Exploration and Target Finding in Cluttered and GPS-Denied Environments","created":"2021-07-19","cited_by_count":1,"area":null},{"id":"2108.00366","title":"Agent-aware State Estimation in Autonomous Vehicles","created":"2021-08-01","cited_by_count":1,"area":null},{"id":"2203.03068","title":"Diversifying Agent's Behaviors in Interactive Decision Models","created":"2022-03-06","cited_by_count":1,"area":null},{"id":"2305.11811","title":"Monte-Carlo Search for an Equilibrium in Dec-POMDPs","created":"2023-05-19","cited_by_count":1,"area":null}],"next_cursor":"100"}