{"total":634,"rows":[{"id":"2310.12567","title":"Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark","created":"2023-10-19","cited_by_count":143,"area":null},{"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":"2206.08686","title":"Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning","created":"2022-06-17","cited_by_count":119,"area":null},{"id":"2304.09870","title":"Heterogeneous-Agent Reinforcement Learning","created":"2023-04-19","cited_by_count":69,"area":null},{"id":"2205.11814","title":"Penalized Proximal Policy Optimization for Safe Reinforcement Learning","created":"2022-05-24","cited_by_count":68,"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":"2202.04129","title":"Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence","created":"2022-02-08","cited_by_count":57,"area":null},{"id":"2209.12941","title":"End-to-End Affordance Learning for Robotic Manipulation","created":"2022-09-26","cited_by_count":57,"area":null},{"id":"2206.09889","title":"Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world","created":"2022-06-20","cited_by_count":56,"area":null},{"id":"2110.14300","title":"Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks","created":"2021-10-27","cited_by_count":54,"area":null},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"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":"2209.10485","title":"Towards a Standardised Performance Evaluation Protocol for Cooperative MARL","created":"2022-09-21","cited_by_count":49,"area":null},{"id":"2106.03352","title":"The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces","created":"2021-06-07","cited_by_count":48,"area":null},{"id":"2405.08550","title":"Learning Multi-Agent Communication from Graph Modeling Perspective","created":"2024-05-14","cited_by_count":48,"area":null},{"id":"2108.08612","title":"Settling the Variance of Multi-Agent Policy Gradients","created":"2021-08-19","cited_by_count":45,"area":null},{"id":"2406.14558","title":"CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics","created":"2024-06-20","cited_by_count":44,"area":null},{"id":"2302.01605","title":"Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased","created":"2023-02-03","cited_by_count":37,"area":null},{"id":"2211.02127","title":"Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation","created":"2022-11-03","cited_by_count":36,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2307.16212","title":"Robust Multi-Agent Reinforcement Learning with State Uncertainty","created":"2023-07-30","cited_by_count":36,"area":null},{"id":"2505.05108","title":"Multi-agent Embodied AI: Advances and Future Directions","created":"2025-05-08","cited_by_count":36,"area":null},{"id":"2309.05655","title":"Dynamic Handover: Throw and Catch with Bimanual Hands","created":"2023-09-11","cited_by_count":35,"area":null},{"id":"2309.12825","title":"OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Control","created":"2023-09-22","cited_by_count":33,"area":null},{"id":"2312.01472","title":"BenchMARL: Benchmarking Multi-Agent Reinforcement Learning","created":"2023-12-03","cited_by_count":33,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2311.12495","title":"Multi-Objective Reinforcement Learning Based on Decomposition: A Taxonomy and Framework","created":"2023-11-21","cited_by_count":31,"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":"2312.05162","title":"A Review of Cooperation in Multi-agent Learning","created":"2023-12-08","cited_by_count":29,"area":null},{"id":"2112.01280","title":"Learning Graphon Mean Field Games and Approximate Nash Equilibria","created":"2021-11-29","cited_by_count":28,"area":null},{"id":"2211.04324","title":"Machine Learning-Aided Operations and Communications of Unmanned Aerial Vehicles: A Contemporary Survey","created":"2022-11-07","cited_by_count":28,"area":null},{"id":"2305.03286","title":"Composite Motion Learning with Task Control","created":"2023-05-05","cited_by_count":28,"area":null},{"id":"2407.13237","title":"LLM-Empowered State Representation for Reinforcement Learning","created":"2024-07-18","cited_by_count":28,"area":null},{"id":"2302.03673","title":"Breaking the Curse of Multiagents in a Large State Space: RL in Markov Games with Independent Linear Function Approximation","created":"2023-02-07","cited_by_count":27,"area":null},{"id":"2111.04613","title":"Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems","created":"2021-11-08","cited_by_count":26,"area":null},{"id":"2301.06387","title":"PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordination","created":"2023-01-16","cited_by_count":25,"area":null},{"id":"2310.10810","title":"Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms","created":"2023-10-16","cited_by_count":25,"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":"2412.11120","title":"Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning","created":"2024-12-15","cited_by_count":23,"area":null},{"id":"2108.01843","title":"Model-Based Opponent Modeling","created":"2021-08-04","cited_by_count":22,"area":null},{"id":"2208.07004","title":"AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N","created":"2022-08-15","cited_by_count":22,"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":"2204.07932","title":"Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learning","created":"2022-04-17","cited_by_count":21,"area":null},{"id":"2210.13708","title":"MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Library","created":"2022-10-11","cited_by_count":21,"area":null},{"id":"2407.14931","title":"POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding","created":"2024-07-20","cited_by_count":21,"area":null},{"id":"2412.05255","title":"TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft","created":"2024-12-06","cited_by_count":21,"area":null},{"id":"2310.08348","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","created":"2023-10-12","cited_by_count":20,"area":null},{"id":"2110.05734","title":"Learning Efficient Multi-Agent Cooperative Visual Exploration","created":"2021-10-12","cited_by_count":19,"area":null},{"id":"2202.00104","title":"Generalization in Cooperative Multi-Agent Systems","created":"2022-01-31","cited_by_count":19,"area":null},{"id":"2209.12681","title":"More Centralized Training, Still Decentralized Execution: Multi-Agent Conditional Policy Factorization","created":"2022-09-26","cited_by_count":19,"area":null},{"id":"2211.12712","title":"Contrastive Identity-Aware Learning for Multi-Agent Value Decomposition","created":"2022-11-23","cited_by_count":19,"area":null},{"id":"2302.12232","title":"Concept Learning for Interpretable Multi-Agent Reinforcement Learning","created":"2023-02-23","cited_by_count":19,"area":null},{"id":"2306.10715","title":"Maximum Entropy Heterogeneous-Agent Reinforcement Learning","created":"2023-06-19","cited_by_count":19,"area":null},{"id":"2307.01158","title":"Theory of Mind as Intrinsic Motivation for Multi-Agent Reinforcement Learning","created":"2023-07-03","cited_by_count":19,"area":null},{"id":"2310.13565","title":"Reward Shaping for Happier Autonomous Cyber Security Agents","created":"2023-10-20","cited_by_count":19,"area":null},{"id":"2107.01151","title":"Collaborative Visual Navigation","created":"2021-07-02","cited_by_count":18,"area":null},{"id":"2209.10113","title":"Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning","created":"2022-09-20","cited_by_count":18,"area":null},{"id":"2301.03398","title":"Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative Exploration","created":"2023-01-09","cited_by_count":18,"area":null},{"id":"2305.17352","title":"Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?","created":"2023-05-27","cited_by_count":18,"area":null},{"id":"2302.03322","title":"Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence","created":"2023-02-07","cited_by_count":17,"area":null},{"id":"2306.09318","title":"Inroads into Autonomous Network Defence using Explained Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2410.17351","title":"Hierarchical Multi-agent Reinforcement Learning for Cyber Network Defense","created":"2024-10-22","cited_by_count":17,"area":null},{"id":"2203.07676","title":"An Introduction to Multi-Agent Reinforcement Learning and Review of its Application to Autonomous Mobility","created":"2022-03-15","cited_by_count":16,"area":null},{"id":"2205.07229","title":"RoMFAC: A robust mean-field actor-critic reinforcement learning against adversarial perturbations on states","created":"2022-05-15","cited_by_count":16,"area":null},{"id":"2206.02640","title":"Policy Optimization for Markov Games: Unified Framework and Faster Convergence","created":"2022-06-06","cited_by_count":16,"area":null},{"id":"2206.12030","title":"Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2210.12124","title":"Equivariant Networks for Zero-Shot Coordination","created":"2022-10-21","cited_by_count":16,"area":null},{"id":"2110.00304","title":"Divergence-Regularized Multi-Agent Actor-Critic","created":"2021-10-01","cited_by_count":15,"area":null},{"id":"2211.16068","title":"ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency","created":"2022-11-29","cited_by_count":15,"area":null},{"id":"2305.05909","title":"Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers","created":"2023-05-10","cited_by_count":15,"area":null},{"id":"2310.15414","title":"Diverse Conventions for Human-AI Collaboration","created":"2023-10-24","cited_by_count":15,"area":null},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","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":"2209.14344","title":"Pareto Actor-Critic for Equilibrium Selection in Multi-Agent Reinforcement Learning","created":"2022-09-28","cited_by_count":14,"area":null},{"id":"2504.21048","title":"Multi-Agent Reinforcement Learning for Resources Allocation Optimization: A Survey","created":"2025-04-29","cited_by_count":14,"area":null},{"id":"2302.02792","title":"Dealing With Non-stationarity in Decentralized Cooperative Multi-Agent Deep Reinforcement Learning via Multi-Timescale Learning","created":"2023-02-06","cited_by_count":13,"area":null},{"id":"2308.09595","title":"Minimum Coverage Sets for Training Robust Ad Hoc Teamwork Agents","created":"2023-08-18","cited_by_count":13,"area":null},{"id":"2310.09727","title":"Provably Fast Convergence of Independent Natural Policy Gradient for Markov Potential Games","created":"2023-10-15","cited_by_count":13,"area":null},{"id":"2312.15600","title":"Context-aware Communication for Multi-agent Reinforcement Learning","created":"2023-12-25","cited_by_count":13,"area":null},{"id":"2406.02081","title":"FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning","created":"2024-06-04","cited_by_count":13,"area":null},{"id":"2407.08164","title":"Hierarchical Consensus-Based Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Tasks","created":"2024-07-11","cited_by_count":13,"area":null},{"id":"2411.07104","title":"Learning Multi-Agent Loco-Manipulation for Long-Horizon Quadrupedal Pushing","created":"2024-11-11","cited_by_count":13,"area":null},{"id":"2412.03338","title":"AI-Driven Day-to-Day Route Choice","created":"2024-12-04","cited_by_count":13,"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":"2203.04735","title":"A Survey on Reinforcement Learning Methods in Character Animation","created":"2022-03-07","cited_by_count":12,"area":null},{"id":"2205.10047","title":"The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure","created":"2022-05-20","cited_by_count":12,"area":null},{"id":"2205.12449","title":"MAVIPER: Learning Decision Tree Policies for Interpretable Multi-Agent Reinforcement Learning","created":"2022-05-25","cited_by_count":12,"area":null},{"id":"2310.05939","title":"Learning Cyber Defence Tactics from Scratch with Multi-Agent Reinforcement Learning","created":"2023-08-25","cited_by_count":12,"area":null},{"id":"2312.15908","title":"Decentralized Monte Carlo Tree Search for Partially Observable Multi-agent Pathfinding","created":"2023-12-26","cited_by_count":12,"area":null},{"id":"2210.08872","title":"PTDE: Personalized Training with Distilled Execution for Multi-Agent Reinforcement Learning","created":"2022-10-17","cited_by_count":11,"area":null},{"id":"2305.13937","title":"Multi-agent Continual Coordination via Progressive Task Contextualization","created":"2023-05-07","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":"2412.04233","title":"HyperMARL: Adaptive Hypernetworks for Multi-Agent RL","created":"2024-12-05","cited_by_count":11,"area":null},{"id":"2506.14990","title":"MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning","created":"2025-06-17","cited_by_count":11,"area":null},{"id":"2111.05992","title":"On the Use and Misuse of Absorbing States in Multi-agent Reinforcement Learning","created":"2021-11-10","cited_by_count":10,"area":null},{"id":"2210.03022","title":"Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning","created":"2022-10-04","cited_by_count":10,"area":null}],"next_cursor":"100"}