{"total":220,"rows":[{"id":"2410.20092","title":"OGBench: Benchmarking Offline Goal-Conditioned RL","created":"2024-10-26","cited_by_count":238,"area":"offlinerl"},{"id":"2410.00425","title":"ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI","created":"2024-10-01","cited_by_count":229,"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":"2304.09870","title":"Heterogeneous-Agent Reinforcement Learning","created":"2023-04-19","cited_by_count":69,"area":null},{"id":"2106.06135","title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","created":"2021-06-11","cited_by_count":66,"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":"2306.16740","title":"Principles and Guidelines for Evaluating Social Robot Navigation Algorithms","created":"2023-06-29","cited_by_count":56,"area":null},{"id":"2303.17503","title":"Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning","created":"2023-03-29","cited_by_count":51,"area":null},{"id":"2310.02172","title":"Lyfe Agents: Generative agents for low-cost real-time social interactions","created":"2023-10-03","cited_by_count":49,"area":"agents"},{"id":"2407.17032","title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","created":"2024-07-24","cited_by_count":46,"area":"deeprl"},{"id":"2210.06835","title":"Multi-agent Dynamic Algorithm Configuration","created":"2022-10-13","cited_by_count":36,"area":null},{"id":"2402.16499","title":"LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments","created":"2024-02-26","cited_by_count":36,"area":"agents"},{"id":"2505.05108","title":"Multi-agent Embodied AI: Advances and Future Directions","created":"2025-05-08","cited_by_count":36,"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":"2302.06205","title":"Order Matters: Agent-by-agent Policy Optimization","created":"2023-02-13","cited_by_count":24,"area":null},{"id":"2406.12905","title":"PufferLib: Making Reinforcement Learning Libraries and Environments Play Nice","created":"2024-06-11","cited_by_count":24,"area":null},{"id":"2106.07551","title":"MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning","created":"2021-06-05","cited_by_count":23,"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":"2106.07798","title":"Poisoning Deep Reinforcement Learning Agents with In-Distribution Triggers","created":"2021-06-14","cited_by_count":20,"area":"safety"},{"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":"2306.10715","title":"Maximum Entropy Heterogeneous-Agent Reinforcement Learning","created":"2023-06-19","cited_by_count":19,"area":null},{"id":"2401.17173","title":"Zero-Shot Reinforcement Learning via Function Encoders","created":"2024-01-30","cited_by_count":18,"area":"deeprl"},{"id":"2111.05969","title":"PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems","created":"2021-11-10","cited_by_count":16,"area":null},{"id":"2211.10649","title":"LibSignal: An Open Library for Traffic Signal Control","created":"2022-11-19","cited_by_count":16,"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":"2305.17568","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":"2201.08484","title":"Iterated Reasoning with Mutual Information in Cooperative and Byzantine Decentralized Teaming","created":"2022-01-20","cited_by_count":14,"area":null},{"id":"2302.13851","title":"Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attacks","created":"2023-02-27","cited_by_count":14,"area":null},{"id":"2304.13269","title":"Games for Artificial Intelligence Research: A Review and Perspectives","created":"2023-04-26","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":"2110.06396","title":"GridLearn: Multiagent Reinforcement Learning for Grid-Aware Building Energy Management","created":"2021-10-12","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":"2407.08590","title":"A Review of Nine Physics Engines for Reinforcement Learning Research","created":"2024-07-11","cited_by_count":12,"area":"deeprl"},{"id":"2102.12550","title":"Learning Emergent Discrete Message Communication for Cooperative Reinforcement Learning","created":"2021-02-24","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":"2112.07013","title":"PantheonRL: A MARL Library for Dynamic Training Interactions","created":"2021-12-13","cited_by_count":10,"area":null},{"id":"2311.15341","title":"Generative Modelling of Stochastic Actions with Arbitrary Constraints in Reinforcement Learning","created":"2023-11-26","cited_by_count":10,"area":null},{"id":"2405.18942","title":"Verifiably Robust Conformal Prediction","created":"2024-05-29","cited_by_count":10,"area":null},{"id":"2502.03723","title":"Speaking the Language of Teamwork: LLM-Guided Credit Assignment in Multi-Agent Reinforcement Learning","created":"2025-02-06","cited_by_count":10,"area":"agents"},{"id":"2301.05334","title":"TransfQMix: Transformers for Leveraging the Graph Structure of Multi-Agent Reinforcement Learning Problems","created":"2023-01-13","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":"2312.04940","title":"Canaries and Whistles: Resilient Drone Communication Networks with (or without) Deep Reinforcement Learning","created":"2023-12-08","cited_by_count":9,"area":null},{"id":"2107.09598","title":"Learning Altruistic Behaviours in Reinforcement Learning without External Rewards","created":"2021-07-20","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":"2404.00413","title":"Language Models are Spacecraft Operators","created":"2024-03-30","cited_by_count":8,"area":null},{"id":"2603.00730","title":"MO-MIX: Multi-Objective Multi-Agent Cooperative Decision-Making With Deep Reinforcement Learning","created":"2026-02-28","cited_by_count":8,"area":null},{"id":"2206.10158","title":"Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems","created":"2022-06-21","cited_by_count":7,"area":null},{"id":"2501.01593","title":"BLAST: A Stealthy Backdoor Leverage Attack against Cooperative Multi-Agent Deep Reinforcement Learning based Systems","created":"2025-01-03","cited_by_count":7,"area":"safety"},{"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":"2505.18334","title":"CoopReflect: Towards Natural Language Communication for Cooperative Autonomous Driving via Multi-Agent Learning","created":"2025-05-23","cited_by_count":7,"area":"driving"},{"id":"2506.04147","title":"SLAC: Safe and Efficient Real-Robot Reinforcement Learning via Unsupervised Simulation Pre-Training","created":"2025-06-04","cited_by_count":7,"area":"deeprl"},{"id":"2507.05178","title":"CREW-WILDFIRE: Benchmarking Agentic Multi-Agent Collaborations at Scale","created":"2025-07-07","cited_by_count":7,"area":"agents"},{"id":"2510.26389","title":"Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning","created":"2025-10-30","cited_by_count":7,"area":null},{"id":"2110.05597","title":"Learning to Coordinate in Multi-Agent Systems: A Coordinated Actor-Critic Algorithm and Finite-Time Guarantees","created":"2021-10-11","cited_by_count":6,"area":null},{"id":"2206.10944","title":"POGEMA: Partially Observable Grid Environment for Multiple Agents","created":"2022-06-22","cited_by_count":6,"area":null},{"id":"2407.16312","title":"MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning","created":"2024-07-23","cited_by_count":6,"area":null},{"id":"2502.02844","title":"Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning","created":"2025-02-05","cited_by_count":6,"area":null},{"id":"2506.02387","title":"VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments","created":"2025-06-03","cited_by_count":6,"area":"mllm"},{"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":"2111.01100","title":"Investigation of Independent Reinforcement Learning Algorithms in Multi-Agent Environments","created":"2021-11-01","cited_by_count":5,"area":null},{"id":"2303.05584","title":"SOCIALGYM 2.0: Simulator for Multi-Agent Social Robot Navigation in Shared Human Spaces","created":"2023-03-09","cited_by_count":5,"area":null},{"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":"2505.19532","title":"Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning","created":"2025-05-26","cited_by_count":5,"area":"deeprl"},{"id":"2111.00345","title":"Multi-Agent Advisor Q-Learning","created":"2021-10-26","cited_by_count":4,"area":null},{"id":"2401.03546","title":"NovelGym: A Flexible Ecosystem for Hybrid Planning and Learning Agents Designed for Open Worlds","created":"2024-01-07","cited_by_count":4,"area":null},{"id":"2405.18110","title":"Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning","created":"2024-05-28","cited_by_count":4,"area":null},{"id":"2407.03969","title":"Craftium: Bridging Flexibility and Efficiency for Rich 3D Single- and Multi-Agent Environments","created":"2024-07-04","cited_by_count":4,"area":null},{"id":"2505.17734","title":"URB -- Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles","created":"2025-05-23","cited_by_count":4,"area":"driving"},{"id":"2604.00722","title":"LangMARL: Natural Language Multi-Agent Reinforcement Learning","created":"2026-04-01","cited_by_count":4,"area":"agents"},{"id":"2609.19134","title":"ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments","created":"2026-09-16","cited_by_count":4,"area":null},{"id":"2104.05610","title":"A coevolutionary approach to deep multi-agent reinforcement learning","created":"2021-04-12","cited_by_count":3,"area":null},{"id":"2207.08894","title":"A Deep Reinforcement Learning Approach for Finding Non-Exploitable Strategies in Two-Player Atari Games","created":"2022-07-18","cited_by_count":3,"area":null},{"id":"2304.12289","title":"Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics","created":"2023-04-24","cited_by_count":3,"area":null},{"id":"2311.00865","title":"Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning","created":"2023-11-01","cited_by_count":3,"area":null},{"id":"2403.16871","title":"Conformal Off-Policy Prediction for Multi-Agent Systems","created":"2024-03-25","cited_by_count":3,"area":null},{"id":"2403.17805","title":"Scenario-Based Curriculum Generation for Multi-Agent Autonomous Driving","created":"2024-03-26","cited_by_count":3,"area":null},{"id":"2502.20065","title":"RouteRL: Multi-agent reinforcement learning framework for urban route choice with autonomous vehicles","created":"2025-02-27","cited_by_count":3,"area":"driving"},{"id":"2506.10326","title":"VGC-Bench: Towards Mastering Diverse Team Strategies in Competitive Pok\\'emon","created":"2025-06-12","cited_by_count":3,"area":null},{"id":"2508.02912","title":"Communicating Plans, Not Percepts: Scalable Multi-Agent Coordination with Embodied World Models","created":"2025-08-04","cited_by_count":3,"area":"wm"},{"id":"2603.06413","title":"A Reference Architecture of Reinforcement Learning Frameworks","created":"2026-03-06","cited_by_count":3,"area":"deeprl"},{"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":"2206.12330","title":"Toward multi-target self-organizing pursuit in a partially observable Markov game","created":"2022-06-24","cited_by_count":2,"area":null},{"id":"2302.07337","title":"Graph Attention Multi-Agent Fleet Autonomy for Advanced Air Mobility","created":"2023-02-14","cited_by_count":2,"area":null},{"id":"2311.17190","title":"Minimax Exploiter: A Data Efficient Approach for Competitive Self-Play","created":"2023-11-28","cited_by_count":2,"area":null},{"id":"2401.07056","title":"Aquarium: A Comprehensive Framework for Exploring Predator-Prey Dynamics through Multi-Agent Reinforcement Learning Algorithms","created":"2024-01-13","cited_by_count":2,"area":null},{"id":"2405.18123","title":"PyTAG: Tabletop Games for Multi-Agent Reinforcement Learning","created":"2024-05-28","cited_by_count":2,"area":null},{"id":"2411.11318","title":"Syllabus: Portable Curricula for Reinforcement Learning Agents","created":"2024-11-18","cited_by_count":2,"area":"deeprl"},{"id":"2502.15425","title":"TAG: A Decentralized Framework for Multi-Agent Hierarchical Reinforcement Learning","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2503.04262","title":"Guidelines for Applying RL and MARL in Cybersecurity Applications","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2506.09434","title":"When Is Diversity Rewarded in Cooperative Multi-Agent Learning?","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2509.12927","title":"HLSMAC: A New StarCraft Multi-Agent Challenge for High-Level Strategic Decision-Making","created":"2025-09-16","cited_by_count":2,"area":"agents"},{"id":"2510.14503","title":"Learning to Undo: Rollback-Augmented Reinforcement Learning with Reversibility Signals","created":"2025-10-16","cited_by_count":2,"area":"deeprl"},{"id":"2510.27659","title":"Challenges in Credit Assignment for Multi-Agent Reinforcement Learning in Open Agent Systems","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2511.04646","title":"DR. WELL: Dynamic Reasoning and Learning with Symbolic World Model for Embodied LLM-Based Multi-Agent Collaboration","created":"2025-11-06","cited_by_count":2,"area":"wm"},{"id":"2601.15015","title":"Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control","created":"2026-01-21","cited_by_count":2,"area":"deeprl"},{"id":"2602.21515","title":"Training Generalizable Collaborative Agents via Strategic Risk Aversion","created":"2026-02-25","cited_by_count":2,"area":"agents"},{"id":"2102.09824","title":"Sim-Env: Decoupling OpenAI Gym Environments from Simulation Models","created":"2021-02-19","cited_by_count":1,"area":null},{"id":"2109.09034","title":"Greedy UnMixing for Q-Learning in Multi-Agent Reinforcement Learning","created":"2021-09-19","cited_by_count":1,"area":null}],"next_cursor":"100"}