{"total":294,"rows":[{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942,"area":null},{"id":"2109.12674","title":"MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning","created":"2021-09-26","cited_by_count":290,"area":"wm"},{"id":"2109.11251","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","created":"2021-09-23","cited_by_count":186,"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":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78,"area":"deeprl"},{"id":"2412.01928","title":"MALT: Improving Reasoning with Multi-Agent LLM Training","created":"2024-12-02","cited_by_count":76,"area":"lr"},{"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":"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":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60,"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":"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":"2301.07137","title":"Heterogeneous Multi-Robot Reinforcement Learning","created":"2023-01-17","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":"2110.13827","title":"Learning to Simulate Self-Driven Particles System with Coordinated Policy Optimization","created":"2021-10-26","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":"2206.07505","title":"Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning","created":"2022-06-15","cited_by_count":32,"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":"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":"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":"2205.15023","title":"Scalable Multi-Agent Model-Based Reinforcement Learning","created":"2022-05-25","cited_by_count":25,"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":"2302.06205","title":"Order Matters: Agent-by-agent Policy Optimization","created":"2023-02-13","cited_by_count":24,"area":null},{"id":"2108.01843","title":"Model-Based Opponent Modeling","created":"2021-08-04","cited_by_count":22,"area":null},{"id":"2407.11384","title":"InvAgent: A Large Language Model based Multi-Agent System for Inventory Management in Supply Chains","created":"2024-07-16","cited_by_count":22,"area":"agents"},{"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":"2202.00104","title":"Generalization in Cooperative Multi-Agent Systems","created":"2022-01-31","cited_by_count":19,"area":null},{"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":"2107.01151","title":"Collaborative Visual Navigation","created":"2021-07-02","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":"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":"2206.02640","title":"Policy Optimization for Markov Games: Unified Framework and Faster Convergence","created":"2022-06-06","cited_by_count":16,"area":null},{"id":"2503.17821","title":"OvercookedV2: Rethinking Overcooked for Zero-Shot Coordination","created":"2025-03-22","cited_by_count":16,"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":"2410.02477","title":"Learning Diverse Bimanual Dexterous Manipulation Skills from Human Demonstrations","created":"2024-10-03","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":"2504.12714","title":"Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination","created":"2025-04-17","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":"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":"2202.00082","title":"Trust Region Bounds for Decentralized PPO Under Non-stationarity","created":"2022-01-31","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":"2412.04233","title":"HyperMARL: Adaptive Hypernetworks for Multi-Agent RL","created":"2024-12-05","cited_by_count":11,"area":null},{"id":"2503.02077","title":"M3HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality","created":"2025-03-03","cited_by_count":11,"area":"agents"},{"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":"2410.01706","title":"Sable: a Performant, Efficient and Scalable Sequence Model for MARL","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2507.13579","title":"Learning to summarize user information for personalized reinforcement learning from human feedback","created":"2025-07-17","cited_by_count":10,"area":"alignment"},{"id":"2511.05005","title":"Multi-agent Coordination via Flow Matching","created":"2025-11-07","cited_by_count":10,"area":"diffusion"},{"id":"2407.20164","title":"Language-Conditioned Offline RL for Multi-Robot Navigation","created":"2024-07-29","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":"2104.07750","title":"Joint Attention for Multi-Agent Coordination and Social Learning","created":"2021-04-15","cited_by_count":8,"area":null},{"id":"2403.17601","title":"LASIL: Learner-Aware Supervised Imitation Learning For Long-term Microscopic Traffic Simulation","created":"2024-03-26","cited_by_count":8,"area":"offlinerl"},{"id":"2408.07841","title":"SustainDC: Benchmarking for Sustainable Data Center Control","created":"2024-08-14","cited_by_count":8,"area":null},{"id":"2503.14576","title":"SocialJax: An Evaluation Suite for Multi-agent Reinforcement Learning in Sequential Social Dilemmas","created":"2025-03-18","cited_by_count":8,"area":null},{"id":"2506.21490","title":"Ad-Hoc Human-AI Coordination Challenge","created":"2025-06-26","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":"2601.21972","title":"Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic","created":"2026-01-29","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":"2402.12416","title":"Aligning Individual and Collective Objectives in Multi-Agent Cooperation","created":"2024-02-19","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":"2404.17780","title":"Verco: Learning Coordinated Verbal Communication for Multi-agent Reinforcement Learning","created":"2024-04-27","cited_by_count":7,"area":"agents"},{"id":"2501.13448","title":"BMG-Q: Localized Bipartite Match Graph Attention Q-Learning for Ride-Pooling Order Dispatch","created":"2025-01-23","cited_by_count":7,"area":"deeprl"},{"id":"2501.13592","title":"WFCRL: A Multi-Agent Reinforcement Learning Benchmark for Wind Farm Control","created":"2025-01-23","cited_by_count":7,"area":null},{"id":"2508.04811","title":"HCRide: Harmonizing Passenger Fairness and Driver Preference for Human-Centered Ride-Hailing","created":"2025-08-06","cited_by_count":7,"area":null},{"id":"2602.15891","title":"Learning to Drive in New Cities Without Human Demonstrations","created":"2026-02-09","cited_by_count":7,"area":"driving"},{"id":"2607.13591","title":"Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents","created":"2026-07-15","cited_by_count":7,"area":"agents"},{"id":"2106.11156","title":"Multi-Agent Curricula and Emergent Implicit Signaling","created":"2021-06-21","cited_by_count":6,"area":null},{"id":"2312.03644","title":"MACCA: Offline Multi-agent Reinforcement Learning with Causal Credit Assignment","created":"2023-12-06","cited_by_count":6,"area":"offlinerl"},{"id":"2402.02097","title":"Settling Decentralized Multi-Agent Coordinated Exploration by Novelty Sharing","created":"2024-02-03","cited_by_count":6,"area":null},{"id":"2409.16720","title":"Dashing for the Golden Snitch: Multi-Drone Time-Optimal Motion Planning with Multi-Agent Reinforcement Learning","created":"2024-09-25","cited_by_count":6,"area":null},{"id":"2503.03796","title":"Human Implicit Preference-Based Policy Fine-tuning for Multi-Agent Reinforcement Learning in USV Swarm","created":"2025-03-05","cited_by_count":6,"area":"agents"},{"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":"2102.10616","title":"Dealing with Non-Stationarity in MARL via Trust-Region Decomposition","created":"2021-02-21","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":"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":"2211.12956","title":"Reinforcement learning for traffic signal control in hybrid action space","created":"2022-11-23","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":"2304.07520","title":"STAS: Spatial-Temporal Return Decomposition for Multi-agent Reinforcement Learning","created":"2023-04-15","cited_by_count":5,"area":null},{"id":"2305.09458","title":"An Empirical Study on Google Research Football Multi-agent Scenarios","created":"2023-05-16","cited_by_count":5,"area":null},{"id":"2306.06236","title":"iPLAN: Intent-Aware Planning in Heterogeneous Traffic via Distributed Multi-Agent Reinforcement Learning","created":"2023-06-09","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":"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":"2503.15703","title":"Predicting Multi-Agent Specialization via Task Parallelizability","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2507.14850","title":"Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems","created":"2025-07-20","cited_by_count":5,"area":null},{"id":"2507.15351","title":"One Step is Enough: Multi-Agent Reinforcement Learning based on One-Step Policy Optimization for Order Dispatch on Ride-Sharing Platforms","created":"2025-07-21","cited_by_count":5,"area":null},{"id":"2510.06913","title":"DecompGAIL: Learning Realistic Traffic Behaviors with Decomposed Multi-Agent Generative Adversarial Imitation Learning","created":"2025-10-08","cited_by_count":5,"area":"offlinerl"},{"id":"2603.01221","title":"Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math Reasoning","created":"2026-03-01","cited_by_count":5,"area":"lr"},{"id":"2605.02801","title":"Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces","created":"2026-05-04","cited_by_count":5,"area":"agents"},{"id":"2211.11043","title":"Revealing Robust Oil and Gas Company Macro-Strategies using Deep Multi-Agent Reinforcement Learning","created":"2022-11-20","cited_by_count":4,"area":null}],"next_cursor":"100"}