{"total":316,"rows":[{"id":"2107.06857","title":"Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot","created":"2021-07-14","cited_by_count":99,"area":null},{"id":"2309.09971","title":"MindAgent: Emergent Gaming Interaction","created":"2023-09-18","cited_by_count":88,"area":null},{"id":"2102.07475","title":"Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing","created":"2021-02-15","cited_by_count":87,"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":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60,"area":null},{"id":"2111.09189","title":"ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind","created":"2021-10-15","cited_by_count":58,"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":"2405.08550","title":"Learning Multi-Agent Communication from Graph Modeling Perspective","created":"2024-05-14","cited_by_count":48,"area":null},{"id":"2106.15691","title":"Deep Multiagent Reinforcement Learning: Challenges and Directions","created":"2021-06-29","cited_by_count":42,"area":null},{"id":"2505.05108","title":"Multi-agent Embodied AI: Advances and Future Directions","created":"2025-05-08","cited_by_count":36,"area":null},{"id":"2103.06426","title":"XDO: A Double Oracle Algorithm for Extensive-Form Games","created":"2021-03-11","cited_by_count":34,"area":null},{"id":"2206.10607","title":"MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer","created":"2022-06-20","cited_by_count":34,"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":"2206.07505","title":"Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning","created":"2022-06-15","cited_by_count":32,"area":null},{"id":"2102.08159","title":"RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents","created":"2021-02-16","cited_by_count":31,"area":null},{"id":"2105.08692","title":"Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition","created":"2021-05-18","cited_by_count":30,"area":null},{"id":"2106.10110","title":"Towards Distraction-Robust Active Visual Tracking","created":"2021-06-18","cited_by_count":30,"area":null},{"id":"2102.07936","title":"DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning","created":"2021-02-16","cited_by_count":26,"area":null},{"id":"2106.00136","title":"Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning","created":"2021-05-31","cited_by_count":25,"area":null},{"id":"2310.05208","title":"ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination","created":"2023-10-08","cited_by_count":24,"area":null},{"id":"2203.08553","title":"PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration","created":"2022-03-16","cited_by_count":23,"area":null},{"id":"2208.11510","title":"Quantum Multi-Agent Meta Reinforcement Learning","created":"2022-08-22","cited_by_count":23,"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":"2103.08067","title":"Quasi-Equivalence Discovery for Zero-Shot Emergent Communication","created":"2021-03-14","cited_by_count":19,"area":null},{"id":"2103.11883","title":"Regularized Softmax Deep Multi-Agent $Q$-Learning","created":"2021-03-22","cited_by_count":19,"area":null},{"id":"2202.00104","title":"Generalization in Cooperative Multi-Agent Systems","created":"2022-01-31","cited_by_count":19,"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":"2204.03516","title":"Distributed Reinforcement Learning for Robot Teams: A Review","created":"2022-04-07","cited_by_count":16,"area":null},{"id":"2205.07229","title":"RoMFAC: A robust mean-field actor-critic reinforcement learning against adversarial perturbations on states","created":"2022-05-15","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":"2112.03547","title":"Self-Organized Polynomial-Time Coordination Graphs","created":"2021-12-07","cited_by_count":15,"area":null},{"id":"2203.04482","title":"Multi-Agent Policy Transfer via Task Relationship Modeling","created":"2022-03-09","cited_by_count":14,"area":null},{"id":"2504.21048","title":"Multi-Agent Reinforcement Learning for Resources Allocation Optimization: A Survey","created":"2025-04-29","cited_by_count":14,"area":null},{"id":"2312.15600","title":"Context-aware Communication for Multi-agent Reinforcement Learning","created":"2023-12-25","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":"2201.01247","title":"Value Functions Factorization with Latent State Information Sharing in Decentralized Multi-Agent Policy Gradients","created":"2022-01-04","cited_by_count":12,"area":null},{"id":"2210.04365","title":"ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Reward","created":"2022-10-09","cited_by_count":11,"area":null},{"id":"2312.05019","title":"Vision-based Learning for Drones: A Survey","created":"2023-12-08","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":"2506.14990","title":"MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning","created":"2025-06-17","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":"2406.04089","title":"On Limitation of Transformer for Learning HMMs","created":"2024-06-06","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":"2212.14749","title":"Asynchronous Hybrid Reinforcement Learning for Latency and Reliability Optimization in the Metaverse over Wireless Communications","created":"2022-12-30","cited_by_count":9,"area":null},{"id":"2307.13453","title":"Monte-Carlo Tree Search for Multi-Agent Pathfinding: Preliminary Results","created":"2023-07-25","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":"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":"2405.11778","title":"Efficient Multi-agent Reinforcement Learning by Planning","created":"2024-05-20","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":"2104.07750","title":"Joint Attention for Multi-Agent Coordination and Social Learning","created":"2021-04-15","cited_by_count":8,"area":null},{"id":"2312.08884","title":"Global Rewards in Multi-Agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems","created":"2023-12-14","cited_by_count":8,"area":null},{"id":"2501.13200","title":"SRMT: Shared Memory for Multi-agent Lifelong Pathfinding","created":"2025-01-22","cited_by_count":8,"area":null},{"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":"2306.06136","title":"Robustness Testing for Multi-Agent Reinforcement Learning: State Perturbations on Critical Agents","created":"2023-06-09","cited_by_count":7,"area":null},{"id":"2310.02435","title":"Multi-Agent Reinforcement Learning Based on Representational Communication for Large-Scale Traffic Signal Control","created":"2023-10-03","cited_by_count":7,"area":null},{"id":"2402.03741","title":"SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems","created":"2024-02-06","cited_by_count":7,"area":null},{"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":"2502.19717","title":"Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning","created":"2025-02-27","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":"2212.05331","title":"Effects of Spectral Normalization in Multi-agent Reinforcement Learning","created":"2022-12-10","cited_by_count":6,"area":null},{"id":"2305.05116","title":"Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generation","created":"2023-05-09","cited_by_count":6,"area":null},{"id":"2307.13957","title":"Heterogeneous Embodied Multi-Agent Collaboration","created":"2023-07-26","cited_by_count":6,"area":null},{"id":"2308.05893","title":"Learning Team-Based Navigation: A Review of Deep Reinforcement Learning Techniques for Multi-Agent Pathfinding","created":"2023-08-11","cited_by_count":6,"area":null},{"id":"2308.11842","title":"${\\rm E}(3)$-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning","created":"2023-08-23","cited_by_count":6,"area":null},{"id":"2312.09009","title":"Adaptive parameter sharing for multi-agent reinforcement learning","created":"2023-12-14","cited_by_count":6,"area":null},{"id":"2401.06308","title":"A Semantic-Aware Multiple Access Scheme for Distributed, Dynamic 6G-Based Applications","created":"2024-01-12","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":"2410.07863","title":"Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Games","created":"2024-10-10","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":"2411.15036","title":"Safe Multi-Agent Reinforcement Learning with Convergence to Generalized Nash Equilibrium","created":"2024-11-22","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":"2503.02992","title":"RAILGUN: A Unified Convolutional Policy for Multi-Agent Path Finding Across Different Environments and Tasks","created":"2025-03-04","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":"2505.06584","title":"JAEGER: Dual-Level Humanoid Whole-Body Controller","created":"2025-05-10","cited_by_count":6,"area":null},{"id":"2505.23686","title":"ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamwork","created":"2025-05-29","cited_by_count":6,"area":null},{"id":"2206.14170","title":"Risk Perspective Exploration in Distributional Reinforcement Learning","created":"2022-06-28","cited_by_count":5,"area":null},{"id":"2302.03439","title":"Ensemble Value Functions for Efficient Exploration in Multi-Agent Reinforcement Learning","created":"2023-02-07","cited_by_count":5,"area":null},{"id":"2302.04445","title":"Quantum Multi-Agent Actor-Critic Networks for Cooperative Mobile Access in Multi-UAV Systems","created":"2023-02-09","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":"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":"2309.14727","title":"Effective Multi-Agent Deep Reinforcement Learning Control with Relative Entropy Regularization","created":"2023-09-26","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":"2312.16248","title":"XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library","created":"2023-12-25","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":"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":"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":"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":"2104.05931","title":"Two-stage training algorithm for AI robot soccer","created":"2021-04-13","cited_by_count":4,"area":null},{"id":"2302.01188","title":"Best Possible Q-Learning","created":"2023-02-02","cited_by_count":4,"area":null},{"id":"2302.03429","title":"Towards Skilled Population Curriculum for Multi-Agent Reinforcement Learning","created":"2023-02-07","cited_by_count":4,"area":null},{"id":"2305.03608","title":"On the Optimality, Stability, and Feasibility of Control Barrier Functions: An Adaptive Learning-Based Approach","created":"2023-05-05","cited_by_count":4,"area":null},{"id":"2305.05898","title":"Mixture of personality improved Spiking actor network for efficient multi-agent cooperation","created":"2023-05-10","cited_by_count":4,"area":null},{"id":"2306.17052","title":"Safe Model-Based Multi-Agent Mean-Field Reinforcement Learning","created":"2023-06-29","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":"2312.07025","title":"Noise Distribution Decomposition based Multi-Agent Distributional Reinforcement Learning","created":"2023-12-12","cited_by_count":4,"area":null},{"id":"2401.11257","title":"Measuring Policy Distance for Multi-Agent Reinforcement Learning","created":"2024-01-20","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}],"next_cursor":"100"}