{"total":79,"rows":[{"id":"2304.09870","title":"Heterogeneous-Agent Reinforcement Learning","created":"2023-04-19","cited_by_count":69,"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":"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":"2303.03376","title":"MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning","created":"2023-03-06","cited_by_count":31,"area":null},{"id":"2409.12889","title":"Can VLMs Play Action Role-Playing Games? Take Black Myth Wukong as a Study Case","created":"2024-09-19","cited_by_count":24,"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":"2311.01753","title":"RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization","created":"2023-11-03","cited_by_count":20,"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":"2503.17821","title":"OvercookedV2: Rethinking Overcooked for Zero-Shot Coordination","created":"2025-03-22","cited_by_count":16,"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":"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":"2506.14990","title":"MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning","created":"2025-06-17","cited_by_count":11,"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":"2307.01676","title":"RaidEnv: Exploring New Challenges in Automated Content Balancing for Boss Raid Games","created":"2023-07-04","cited_by_count":7,"area":null},{"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":"2405.16386","title":"Variational Offline Multi-agent Skill Discovery","created":"2024-05-26","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":"2511.06142","title":"MALinZero: Efficient Low-Dimensional Search for Mastering Complex Multi-Agent Planning","created":"2025-11-08","cited_by_count":5,"area":null},{"id":"2605.00751","title":"NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search","created":"2026-05-01","cited_by_count":5,"area":null},{"id":"2401.13460","title":"Multi-Agent Diagnostics for Robustness via Illuminated Diversity","created":"2024-01-24","cited_by_count":4,"area":null},{"id":"2412.15517","title":"Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning","created":"2024-12-20","cited_by_count":4,"area":null},{"id":"2509.20648","title":"Wonder Wins Ways: Curiosity-Driven Exploration through Multi-Agent Contextual Calibration","created":"2025-09-25","cited_by_count":4,"area":null},{"id":"2408.07098","title":"QTypeMix: Enhancing Multi-Agent Cooperative Strategies through Heterogeneous and Homogeneous Value Decomposition","created":"2024-08-12","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":"2508.18708","title":"Skill-Aligned Fairness in Multi-Agent Learning for Collaboration in Healthcare","created":"2025-08-26","cited_by_count":3,"area":null},{"id":"2602.15776","title":"GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent Systems","created":"2026-02-17","cited_by_count":3,"area":null},{"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":"2503.01440","title":"Trajectory-Class-Aware Multi-Agent Reinforcement Learning","created":"2025-03-03","cited_by_count":2,"area":null},{"id":"2506.19417","title":"Focusing Influence Mechanism for Multi-Agent Reinforcement Learning","created":"2025-06-24","cited_by_count":2,"area":null},{"id":"2507.23604","title":"Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning","created":"2025-07-31","cited_by_count":2,"area":null},{"id":"2508.12845","title":"CAMAR: Continuous Actions Multi-Agent Routing","created":"2025-08-18","cited_by_count":2,"area":null},{"id":"2510.20218","title":"High-order Interactions Modeling for Interpretable Multi-Agent Q-Learning","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2511.04904","title":"Multi-Agent Craftax: Benchmarking Open-Ended Multi-Agent Reinforcement Learning at the Hyperscale","created":"2025-11-07","cited_by_count":2,"area":null},{"id":"2302.02180","title":"Dual Self-Awareness Value Decomposition Framework without Individual Global Max for Cooperative Multi-Agent Reinforcement Learning","created":"2023-02-04","cited_by_count":1,"area":null},{"id":"2303.13808","title":"marl-jax: Multi-Agent Reinforcement Leaning Framework","created":"2023-03-24","cited_by_count":1,"area":null},{"id":"2405.08036","title":"Potentially Optimal Joint Actions Recognition for Cooperative Multi-Agent Reinforcement Learning","created":"2024-05-13","cited_by_count":1,"area":null},{"id":"2505.10484","title":"Fixing Incomplete Value Function Decomposition for Multi-Agent Reinforcement Learning","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2505.20579","title":"The challenge of hidden gifts in multi-agent reinforcement learning","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2506.07548","title":"Overcoming Environmental Meta-Stationarity in MARL via Adaptive Curriculum and Counterfactual Group Advantage","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2507.09495","title":"GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective","created":"2025-07-13","cited_by_count":1,"area":null},{"id":"2507.10142","title":"Toward Adaptable Multi-Agent Reinforcement Learning: An Assumption-Aware Review","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2509.19512","title":"The Heterogeneous Multi-Agent Challenge","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2510.11824","title":"Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2602.06476","title":"Prism: Spectral Parameter Sharing for Multi-Agent Reinforcement Learning","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2605.18024","title":"Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2606.29126","title":"HiComm: Hierarchical Communication for Multi-agent Reinforcement Learning","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2308.11924","title":"Diverse Policies Converge in Reward-free Markov Decision Processe","created":"2023-08-23","cited_by_count":0,"area":null},{"id":"2409.07189","title":"AI-Guided Molecular Simulations in VR: Exploring Strategies for Imitation Learning in Hyperdimensional Molecular Systems","created":"2024-09-11","cited_by_count":0,"area":null},{"id":"2410.15876","title":"FlickerFusion: Intra-trajectory Domain Generalizing Multi-Agent RL","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2412.15639","title":"Tacit Learning with Adaptive Information Selection for Cooperative Multi-Agent Reinforcement Learning","created":"2024-12-20","cited_by_count":0,"area":null},{"id":"2502.00345","title":"CTC: The Composite Task Challenge for Cooperative Multi-Agent Reinforcement Learning","created":"2025-02-01","cited_by_count":0,"area":null},{"id":"2505.08630","title":"Credit Assignment and Efficient Exploration based on Influence Scope in Multi-agent Reinforcement Learning","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2507.18333","title":"Remembering the Markov Property in Cooperative MARL","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2508.09275","title":"Constrained Black-Box Attacks Against Cooperative Multi-Agent Reinforcement Learning","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2511.14135","title":"AdaFair-MARL: Enforcing Adaptive Fairness Constraints in Multi-Agent Reinforcement Learning","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2512.16444","title":"StarCraft+: Benchmarking Multi-agent Algorithms in Adversary Paradigm","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2602.00676","title":"OpenGuanDan: A Large-Scale Imperfect Information Game Benchmark","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2602.01665","title":"TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.17737","title":"NestRL: A Nested Training Regime for Mutual Adaptation in Human-AI Teaming","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.06608","title":"Two-Bridge: Exclusive Objectives and Extended Horizon StarCraft II Benchmark","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2604.05297","title":"Breakthrough the Suboptimal Stable Point in Value-Factorization-Based Multi-Agent Reinforcement Learning","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.08944","title":"Multi-Agent Decision-Focused Learning via Value-Aware Sequential Communication","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.15044","title":"CoGrid & the Multi-User Gymnasium: A Framework for Multi-Agent Experimentation","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.27162","title":"A High-Throughput Compute-Efficient POMDP Hide-And-Seek-Engine (HASE) for Multi-Agent Operations","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.01805","title":"MAGIC: Multi-Step Advantage-Gated Causal Influence for Multi-agent Reinforcement Learning","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2605.09212","title":"Rethinking Ratio-Based Trust Regions for Policy Optimization in Multi-Agent Reinforcement Learning","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.11880","title":"Adaptive TD-Lambda for Cooperative Multi-agent Reinforcement Learning","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.17393","title":"Heterogeneous Information-Bottleneck Coordination Graphs for Multi-Agent Reinforcement Learning","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2606.25335","title":"Stagnant Neuron: Towards Understanding the Plasticity Loss in Multi-Agent Reinforcement Learning Value Factorization Methods","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.25389","title":"Offline Multi-agent Continual Cooperation via Skill Partition and Reuse","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.29541","title":"Learned Coordination Conventions in Cooperative MARL: Measuring the Translation Gap Between Theory-Informed Roles and Learned Routing","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2606.30072","title":"ACPO: Agent-Chained Policy Optimization for Multi-Agent Reinforcement Learning","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.16524","title":"Feedback Attribution and Representation Geometry: Metrics for Comparing Individual and Shared Rewards in MARL","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2607.29577","title":"DungeonBench: A Benchmark for Rules-Rich Tactical Reasoning in Dungeons & Dragons Combat","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.32594","title":"MA-FPPO: Multi-Agent Flow-Pretrained Policy Optimization","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.34459","title":"Escaping Local Views: Discovering Latent Concepts for Interpretable Multi-Agent Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38889","title":"VERA: Verifiable Feasibility Representations with Counterfactual Credit for Constrained Multi-Agent Control","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.15969","title":"PopGen: Generating Semantically Diverse Populations for Zero-Shot Coordination","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}