{"total":186,"rows":[{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2205.14953","title":"Multi-Agent Reinforcement Learning is a Sequence Modeling Problem","created":"2022-05-30","cited_by_count":155,"area":null},{"id":"2310.12567","title":"Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark","created":"2023-10-19","cited_by_count":143,"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":"2311.10090","title":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","created":"2023-11-16","cited_by_count":63,"area":null},{"id":"2504.16129","title":"MARFT: Multi-Agent Reinforcement Fine-Tuning","created":"2025-04-21","cited_by_count":52,"area":"agents"},{"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":"2405.08550","title":"Learning Multi-Agent Communication from Graph Modeling Perspective","created":"2024-05-14","cited_by_count":48,"area":null},{"id":"2405.14314","title":"Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration","created":"2024-05-23","cited_by_count":45,"area":"lr"},{"id":"2307.11620","title":"Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization","created":"2023-07-21","cited_by_count":43,"area":"offlinerl"},{"id":"2311.13884","title":"Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach","created":"2023-11-23","cited_by_count":38,"area":"agents"},{"id":"2110.10614","title":"Independent Natural Policy Gradient Always Converges in Markov Potential Games","created":"2021-10-20","cited_by_count":37,"area":null},{"id":"2309.12696","title":"Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning","created":"2023-09-22","cited_by_count":37,"area":"offlinerl"},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2110.02793","title":"Multi-Agent Constrained Policy Optimisation","created":"2021-10-06","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":"2112.02845","title":"Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Tasks","created":"2021-12-06","cited_by_count":32,"area":"offlinerl"},{"id":"2206.07505","title":"Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning","created":"2022-06-15","cited_by_count":32,"area":null},{"id":"2201.02373","title":"Mirror Learning: A Unifying Framework of Policy Optimisation","created":"2022-01-07","cited_by_count":31,"area":null},{"id":"2204.08125","title":"FedKL: Tackling Data Heterogeneity in Federated Reinforcement Learning by Penalizing KL Divergence","created":"2022-04-18","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":"2503.13415","title":"A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectives","created":"2025-03-17","cited_by_count":27,"area":"agents"},{"id":"2408.01072","title":"A Survey on Self-play Methods in Reinforcement Learning","created":"2024-08-02","cited_by_count":26,"area":"deeprl"},{"id":"2302.06205","title":"Order Matters: Agent-by-agent Policy Optimization","created":"2023-02-13","cited_by_count":24,"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":"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":"2306.10715","title":"Maximum Entropy Heterogeneous-Agent Reinforcement Learning","created":"2023-06-19","cited_by_count":19,"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":"2405.15821","title":"Reinforcing Language Agents via Policy Optimization with Action Decomposition","created":"2024-05-23","cited_by_count":16,"area":"agents"},{"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":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2603.02604","title":"Heterogeneous Agent Collaborative Reinforcement Learning","created":"2026-03-03","cited_by_count":15,"area":"agents"},{"id":"2208.01682","title":"Heterogeneous-Agent Mirror Learning: A Continuum of Solutions to Cooperative MARL","created":"2022-08-02","cited_by_count":12,"area":null},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2202.00082","title":"Trust Region Bounds for Decentralized PPO Under Non-stationarity","created":"2022-01-31","cited_by_count":11,"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":"2408.10556","title":"Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks","created":"2024-08-20","cited_by_count":11,"area":"offlinerl"},{"id":"2506.14990","title":"MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning","created":"2025-06-17","cited_by_count":11,"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},{"id":"2311.02194","title":"AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction Estimation","created":"2023-11-03","cited_by_count":10,"area":"offlinerl"},{"id":"2406.15836","title":"Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models","created":"2024-06-22","cited_by_count":10,"area":"wm"},{"id":"2410.01706","title":"Sable: a Performant, Efficient and Scalable Sequence Model for MARL","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2305.06446","title":"Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation","created":"2023-05-10","cited_by_count":9,"area":null},{"id":"2306.11551","title":"IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL","created":"2023-06-20","cited_by_count":9,"area":null},{"id":"2401.09455","title":"Dynamic Routing for Integrated Satellite-Terrestrial Networks: A Constrained Multi-Agent Reinforcement Learning Approach","created":"2023-12-23","cited_by_count":9,"area":null},{"id":"2402.04971","title":"Multi-Sender Persuasion: A Computational Perspective","created":"2024-02-07","cited_by_count":9,"area":null},{"id":"2405.18209","title":"Safe Multi-Agent Reinforcement Learning with Bilevel Optimization in Autonomous Driving","created":"2024-05-28","cited_by_count":9,"area":null},{"id":"2410.02511","title":"Stop Wandering, Find the Keys: LLMs Discriminate Key States for Efficient Multi-Agent Exploration","created":"2024-10-03","cited_by_count":9,"area":"agents"},{"id":"2505.20922","title":"Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective","created":"2025-05-27","cited_by_count":9,"area":"wm"},{"id":"2207.03902","title":"Interaction Pattern Disentangling for Multi-Agent Reinforcement Learning","created":"2022-07-08","cited_by_count":8,"area":null},{"id":"2212.12669","title":"On Realization of Intelligent Decision-Making in the Real World: A Foundation Decision Model Perspective","created":"2022-12-24","cited_by_count":8,"area":null},{"id":"2410.01954","title":"ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization","created":"2024-10-02","cited_by_count":8,"area":"offlinerl"},{"id":"2503.21200","title":"Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation","created":"2025-03-27","cited_by_count":8,"area":null},{"id":"2511.19368","title":"LLM-Driven Stationarity-Aware Expert Demonstrations for Multi-Agent Reinforcement Learning in Mobile Systems","created":"2025-11-24","cited_by_count":8,"area":"agents"},{"id":"2203.08412","title":"CTDS: Centralized Teacher with Decentralized Student for Multi-Agent Reinforcement Learning","created":"2022-03-16","cited_by_count":7,"area":null},{"id":"2404.12824","title":"MAexp: A Generic Platform for RL-based Multi-Agent Exploration","created":"2024-04-19","cited_by_count":7,"area":null},{"id":"2405.20018","title":"Safe Multi-agent Reinforcement Learning with Natural Language Constraints","created":"2024-05-30","cited_by_count":7,"area":"agents"},{"id":"2202.04868","title":"Understanding Value Decomposition Algorithms in Deep Cooperative Multi-Agent Reinforcement Learning","created":"2022-02-10","cited_by_count":6,"area":null},{"id":"2306.02006","title":"MA2CL:Masked Attentive Contrastive Learning for Multi-Agent Reinforcement Learning","created":"2023-06-03","cited_by_count":6,"area":null},{"id":"2310.09833","title":"Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization","created":"2023-10-15","cited_by_count":6,"area":null},{"id":"2404.03869","title":"Heterogeneous Multi-Agent Reinforcement Learning for Zero-Shot Scalable Collaboration","created":"2024-04-05","cited_by_count":6,"area":null},{"id":"2410.02664","title":"Grounded Answers for Multi-agent Decision-making Problem through Generative World Model","created":"2024-10-03","cited_by_count":6,"area":"wm"},{"id":"2509.14680","title":"LEED: A Highly Efficient and Scalable LLM-Empowered Expert Demonstrations Framework for Multi-Agent Reinforcement Learning","created":"2025-09-18","cited_by_count":6,"area":"agents"},{"id":"2202.09422","title":"Communication-Efficient Actor-Critic Methods for Homogeneous Markov Games","created":"2022-02-18","cited_by_count":5,"area":null},{"id":"2207.11143","title":"Towards Global Optimality in Cooperative MARL with the Transformation And Distillation Framework","created":"2022-07-12","cited_by_count":5,"area":null},{"id":"2211.03032","title":"Decentralized Policy Optimization","created":"2022-11-06","cited_by_count":5,"area":null},{"id":"2304.10351","title":"Inducing Stackelberg Equilibrium through Spatio-Temporal Sequential Decision-Making in Multi-Agent Reinforcement Learning","created":"2023-04-20","cited_by_count":5,"area":null},{"id":"2310.00871","title":"COMPOSER: Scalable and Robust Modular Policies for Snake Robots","created":"2023-10-02","cited_by_count":5,"area":null},{"id":"2401.04934","title":"Fully Decentralized Cooperative Multi-Agent Reinforcement Learning: A Survey","created":"2024-01-10","cited_by_count":5,"area":null},{"id":"2401.08728","title":"AgentMixer: Multi-Agent Correlated Policy Factorization","created":"2024-01-16","cited_by_count":5,"area":null},{"id":"2401.13662","title":"The Definitive Guide to Policy Gradients in Deep Reinforcement Learning: Theory, Algorithms and Implementations","created":"2024-01-24","cited_by_count":5,"area":"deeprl"},{"id":"2408.05686","title":"The Bandit Whisperer: Communication Learning for Restless Bandits","created":"2024-08-11","cited_by_count":5,"area":null},{"id":"2412.17707","title":"SMAC-Hard: Enabling Mixed Opponent Strategy Script and Self-play on SMAC","created":"2024-12-23","cited_by_count":5,"area":"deeprl"},{"id":"2502.04773","title":"An Extended Benchmarking of Multi-Agent Reinforcement Learning Algorithms in Complex Fully Cooperative Tasks","created":"2025-02-07","cited_by_count":5,"area":null},{"id":"2512.02350","title":"FOVA: Offline Federated Reinforcement Learning with Mixed-Quality Data","created":"2025-12-02","cited_by_count":5,"area":"offlinerl"},{"id":"2110.14468","title":"DESTA: A Framework for Safe Reinforcement Learning with Markov Games of Intervention","created":"2021-10-27","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":"2305.04819","title":"Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning","created":"2023-05-08","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":"2502.01932","title":"VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic Play","created":"2025-02-04","cited_by_count":4,"area":"deeprl"},{"id":"2502.05573","title":"Low-Rank Agent-Specific Adaptation (LoRASA) for Multi-Agent Policy Learning","created":"2025-02-08","cited_by_count":4,"area":null},{"id":"2505.05968","title":"Offline Multi-agent Reinforcement Learning via Sequential Score Decomposition","created":"2025-05-09","cited_by_count":4,"area":"offlinerl"},{"id":"2508.03864","title":"Evo-MARL: Co-Evolutionary Multi-Agent Reinforcement Learning for Internalized Safety","created":"2025-08-05","cited_by_count":4,"area":"agents"},{"id":"2406.02890","title":"Representation Learning For Efficient Deep Multi-Agent Reinforcement Learning","created":"2024-06-05","cited_by_count":3,"area":null},{"id":"2407.00681","title":"Safe Reinforcement Learning for Power System Control: A Review","created":"2024-06-30","cited_by_count":3,"area":"deeprl"},{"id":"2408.06920","title":"Multi-Agent Continuous Control with Generative Flow Networks","created":"2024-08-13","cited_by_count":3,"area":null},{"id":"2409.01092","title":"Two-Timescale Synchronization and Migration for Digital Twin Networks: A Multi-Agent Deep Reinforcement Learning Approach","created":"2024-09-02","cited_by_count":3,"area":null},{"id":"2410.19372","title":"Toward Finding Strong Pareto Optimal Policies in Multi-Agent Reinforcement Learning","created":"2024-10-25","cited_by_count":3,"area":null},{"id":"2410.21109","title":"Dual-Agent Deep Reinforcement Learning for Dynamic Pricing and Replenishment","created":"2024-10-28","cited_by_count":3,"area":"deeprl"},{"id":"2507.18059","title":"Multi-Agent Guided Policy Optimization","created":"2025-07-24","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":"2510.23535","title":"Sequential Multi-Agent Dynamic Algorithm Configuration","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2302.09605","title":"Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learning","created":"2023-02-19","cited_by_count":2,"area":"offlinerl"},{"id":"2308.14308","title":"Policy Diversity for Cooperative Agents","created":"2023-08-28","cited_by_count":2,"area":null},{"id":"2401.17880","title":"Graph Attention-based Reinforcement Learning for Trajectory Design and Resource Assignment in Multi-UAV Assisted Communication","created":"2024-01-31","cited_by_count":2,"area":"deeprl"},{"id":"2402.14090","title":"Social Environment Design","created":"2024-02-21","cited_by_count":2,"area":null},{"id":"2407.12505","title":"Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments","created":"2024-07-17","cited_by_count":2,"area":"deeprl"},{"id":"2410.19382","title":"Multi-Agent Reinforcement Learning with Selective State-Space Models","created":"2024-10-25","cited_by_count":2,"area":"ssm"}],"next_cursor":"100"}