{"total":178,"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":"2212.07489","title":"SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning","created":"2022-12-14","cited_by_count":122,"area":null},{"id":"2305.17330","title":"MADiff: Offline Multi-agent Learning with Diffusion Models","created":"2023-05-27","cited_by_count":75,"area":"diffusion"},{"id":"2304.09870","title":"Heterogeneous-Agent Reinforcement Learning","created":"2023-04-19","cited_by_count":69,"area":null},{"id":"2102.03479","title":"Rethinking the Implementation Tricks and Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learning","created":"2021-02-06","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":"2111.11188","title":"Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification","created":"2021-11-22","cited_by_count":61,"area":"offlinerl"},{"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":"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":"2108.08612","title":"Settling the Variance of Multi-Agent Policy Gradients","created":"2021-08-19","cited_by_count":45,"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":"2110.02793","title":"Multi-Agent Constrained Policy Optimisation","created":"2021-10-06","cited_by_count":35,"area":null},{"id":"2408.09675","title":"Multi-Agent Reinforcement Learning for Autonomous Driving: A Survey","created":"2024-08-19","cited_by_count":32,"area":"driving"},{"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":"2401.11963","title":"Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms","created":"2024-01-22","cited_by_count":26,"area":"deeprl"},{"id":"2210.12566","title":"Solving Continuous Control via Q-learning","created":"2022-10-22","cited_by_count":24,"area":null},{"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":"2407.14931","title":"POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding","created":"2024-07-20","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":"2402.13777","title":"Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions","created":"2024-02-21","cited_by_count":20,"area":"offlinerl"},{"id":"2305.17198","title":"A Model-Based Solution to the Offline Multi-Agent Reinforcement Learning Coordination Problem","created":"2023-05-26","cited_by_count":19,"area":"offlinerl"},{"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":"2107.01460","title":"Mava: a research library for distributed multi-agent reinforcement learning in JAX","created":"2021-07-03","cited_by_count":16,"area":null},{"id":"2210.15479","title":"Low-Rank Modular Reinforcement Learning via Muscle Synergy","created":"2022-10-26","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":"2305.17568","title":"Scalable Primal-Dual Actor-Critic Method for Safe Multi-Agent RL with General Utilities","created":"2023-05-27","cited_by_count":15,"area":null},{"id":"2307.01472","title":"Improving Generalization and Data Efficiency with Diffusion in Offline Multi-agent RL","created":"2023-07-04","cited_by_count":15,"area":"diffusion"},{"id":"2210.17375","title":"ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation","created":"2022-10-26","cited_by_count":14,"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":"2502.19652","title":"Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning","created":"2025-02-27","cited_by_count":13,"area":"deeprl"},{"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":"2211.15612","title":"Learning from Good Trajectories in Offline Multi-Agent Reinforcement Learning","created":"2022-11-28","cited_by_count":12,"area":"offlinerl"},{"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":"2306.11488","title":"Informed POMDP: Leveraging Additional Information in Model-Based RL","created":"2023-06-20","cited_by_count":11,"area":"wm"},{"id":"2412.04233","title":"HyperMARL: Adaptive Hypernetworks for Multi-Agent RL","created":"2024-12-05","cited_by_count":11,"area":null},{"id":"2306.07542","title":"A Versatile Multi-Agent Reinforcement Learning Benchmark for Inventory Management","created":"2023-06-13","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":"2408.14597","title":"On Centralized Critics in Multi-Agent Reinforcement Learning","created":"2024-08-26","cited_by_count":10,"area":null},{"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":"2511.05005","title":"Multi-agent Coordination via Flow Matching","created":"2025-11-07","cited_by_count":10,"area":"diffusion"},{"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":"2308.11272","title":"FoX: Formation-aware exploration in multi-agent reinforcement learning","created":"2023-08-22","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":"2405.11778","title":"Efficient Multi-agent Reinforcement Learning by Planning","created":"2024-05-20","cited_by_count":9,"area":null},{"id":"2406.09068","title":"Dispelling the Mirage of Progress in Offline MARL through Standardised Baselines and Evaluation","created":"2024-06-13","cited_by_count":9,"area":"offlinerl"},{"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":"2302.00521","title":"Off-the-Grid MARL: Datasets with Baselines for Offline Multi-Agent Reinforcement Learning","created":"2023-02-01","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":"2508.06269","title":"OM2P: Offline Multi-Agent Mean-Flow Policy","created":"2025-08-08","cited_by_count":8,"area":"offlinerl"},{"id":"2404.04253","title":"Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolution","created":"2024-04-05","cited_by_count":7,"area":"deeprl"},{"id":"2405.20018","title":"Safe Multi-agent Reinforcement Learning with Natural Language Constraints","created":"2024-05-30","cited_by_count":7,"area":"agents"},{"id":"2502.19717","title":"Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2506.00439","title":"RLAE: Reinforcement Learning-Assisted Ensemble for LLMs","created":"2025-05-31","cited_by_count":7,"area":null},{"id":"2204.09418","title":"Mingling Foresight with Imagination: Model-Based Cooperative Multi-Agent Reinforcement Learning","created":"2022-04-20","cited_by_count":6,"area":null},{"id":"2410.08540","title":"Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning","created":"2024-10-11","cited_by_count":6,"area":null},{"id":"2502.04028","title":"Deep Meta Coordination Graphs for Multi-agent Reinforcement Learning","created":"2025-02-06","cited_by_count":6,"area":null},{"id":"2504.15425","title":"Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL","created":"2025-04-21","cited_by_count":6,"area":null},{"id":"2202.09422","title":"Communication-Efficient Actor-Critic Methods for Homogeneous Markov Games","created":"2022-02-18","cited_by_count":5,"area":null},{"id":"2209.08244","title":"MA2QL: A Minimalist Approach to Fully Decentralized Multi-Agent Reinforcement Learning","created":"2022-09-17","cited_by_count":5,"area":null},{"id":"2211.03032","title":"Decentralized Policy Optimization","created":"2022-11-06","cited_by_count":5,"area":null},{"id":"2212.07684","title":"Multi-Agent Reinforcement Learning with Shared Resources for Inventory Management","created":"2022-12-15","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":"2305.10091","title":"Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2305.18875","title":"Centralised rehearsal of decentralised cooperation: Multi-agent reinforcement learning for the scalable coordination of residential energy flexibility","created":"2023-05-30","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":"2405.10310","title":"Stochastic Q-learning for Large Discrete Action Spaces","created":"2024-05-16","cited_by_count":5,"area":"deeprl"},{"id":"2407.01343","title":"Coordination Failure in Cooperative Offline MARL","created":"2024-07-01","cited_by_count":5,"area":"offlinerl"},{"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":"2302.01188","title":"Best Possible Q-Learning","created":"2023-02-02","cited_by_count":4,"area":null},{"id":"2304.06011","title":"MABL: Bi-Level Latent-Variable World Model for Sample-Efficient Multi-Agent Reinforcement Learning","created":"2023-04-12","cited_by_count":4,"area":"wm"},{"id":"2305.19891","title":"Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2306.17411","title":"Decentralized Motor Skill Learning for Complex Robotic Systems","created":"2023-06-30","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":"2409.12001","title":"Putting Data at the Centre of Offline Multi-Agent Reinforcement Learning","created":"2024-09-18","cited_by_count":4,"area":"offlinerl"},{"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":"2502.08365","title":"Towards Principled Unsupervised Multi-Agent Reinforcement Learning","created":"2025-02-12","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":"2204.12064","title":"PP-MARL: Efficient Privacy-Preserving Multi-Agent Reinforcement Learning for Cooperative Intelligence in Communications","created":"2022-04-26","cited_by_count":3,"area":null},{"id":"2210.05367","title":"Learning Explicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning via Polarization Policy Gradient","created":"2022-10-10","cited_by_count":3,"area":null},{"id":"2309.04615","title":"VDFD: Multi-Agent Value Decomposition Framework with Disentangled World Model","created":"2023-09-08","cited_by_count":3,"area":"wm"},{"id":"2408.06920","title":"Multi-Agent Continuous Control with Generative Flow Networks","created":"2024-08-13","cited_by_count":3,"area":null},{"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":"2509.10656","title":"Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration","created":"2025-09-12","cited_by_count":3,"area":null},{"id":"2601.08237","title":"The End of Reward Engineering: How LLMs Are Redefining Multi-Agent Coordination","created":"2026-01-13","cited_by_count":3,"area":"agents"},{"id":"2602.17062","title":"Retaining Suboptimal Actions to Follow Shifting Optima in Multi-Agent Reinforcement Learning","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2602.18291","title":"Diffusing to Coordinate: Efficient Online Multi-Agent Diffusion Policies","created":"2026-02-20","cited_by_count":3,"area":"diffusion"},{"id":"2604.08174","title":"Value-Guidance MeanFlow for Offline Multi-Agent Reinforcement Learning","created":"2026-04-09","cited_by_count":3,"area":"offlinerl"},{"id":"2203.13319","title":"Remember and Forget Experience Replay for Multi-Agent Reinforcement Learning","created":"2022-03-24","cited_by_count":2,"area":null},{"id":"2206.11420","title":"PAC: Assisted Value Factorisation with Counterfactual Predictions in Multi-Agent Reinforcement Learning","created":"2022-06-22","cited_by_count":2,"area":null},{"id":"2302.08139","title":"Model-Based Decentralized Policy Optimization","created":"2023-02-16","cited_by_count":2,"area":null}],"next_cursor":"100"}