{"total":94,"rows":[{"id":"2106.02195","title":"Celebrating Diversity in Shared Multi-Agent Reinforcement Learning","created":"2021-06-04","cited_by_count":98,"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":"2107.11444","title":"Cooperative Exploration for Multi-Agent Deep Reinforcement Learning","created":"2021-07-23","cited_by_count":57,"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":"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":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","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":"2212.11498","title":"Scalable Multi-Agent Reinforcement Learning for Warehouse Logistics with Robotic and Human Co-Workers","created":"2022-12-22","cited_by_count":30,"area":null},{"id":"2312.05162","title":"A Review of Cooperation in Multi-agent Learning","created":"2023-12-08","cited_by_count":29,"area":null},{"id":"2107.08966","title":"Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration","created":"2021-07-19","cited_by_count":25,"area":null},{"id":"2301.10737","title":"Distributed Control of Partial Differential Equations Using Convolutional Reinforcement Learning","created":"2023-01-25","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":"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":"2209.14344","title":"Pareto Actor-Critic for Equilibrium Selection in Multi-Agent Reinforcement Learning","created":"2022-09-28","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":"2308.09595","title":"Minimum Coverage Sets for Training Robust Ad Hoc Teamwork Agents","created":"2023-08-18","cited_by_count":13,"area":null},{"id":"2204.12568","title":"Toward Policy Explanations for Multi-Agent Reinforcement Learning","created":"2022-04-26","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":"2206.05060","title":"Social Network Structure Shapes Innovation: Experience-sharing in RL with SAPIENS","created":"2022-06-10","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":"2109.12508","title":"LINDA: Multi-Agent Local Information Decomposition for Awareness of Teammates","created":"2021-09-26","cited_by_count":9,"area":null},{"id":"2305.10378","title":"Explainable Multi-Agent Reinforcement Learning for Temporal Queries","created":"2023-05-17","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":"2307.01403","title":"Learning Multi-Agent Communication with Contrastive Learning","created":"2023-07-03","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":"2107.09598","title":"Learning Altruistic Behaviours in Reinforcement Learning without External Rewards","created":"2021-07-20","cited_by_count":8,"area":null},{"id":"2202.01141","title":"Federated Reinforcement Learning for Collective Navigation of Robotic Swarms","created":"2022-02-02","cited_by_count":7,"area":null},{"id":"2301.02083","title":"Self-Motivated Multi-Agent Exploration","created":"2023-01-05","cited_by_count":7,"area":null},{"id":"2205.12880","title":"Trust-based Consensus in Multi-Agent Reinforcement Learning Systems","created":"2022-05-25","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":"2207.02249","title":"Learning Task Embeddings for Teamwork Adaptation in Multi-Agent Reinforcement Learning","created":"2022-07-05","cited_by_count":5,"area":null},{"id":"2212.09586","title":"Learning Latent Representations to Co-Adapt to Humans","created":"2022-12-19","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":"2408.05686","title":"The Bandit Whisperer: Communication Learning for Restless Bandits","created":"2024-08-11","cited_by_count":5,"area":null},{"id":"2303.09032","title":"Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learning","created":"2023-03-16","cited_by_count":4,"area":null},{"id":"2312.08466","title":"Efficiently Quantifying Individual Agent Importance in Cooperative MARL","created":"2023-12-13","cited_by_count":4,"area":null},{"id":"2502.05573","title":"Low-Rank Agent-Specific Adaptation (LoRASA) for Multi-Agent Policy Learning","created":"2025-02-08","cited_by_count":4,"area":null},{"id":"2203.07092","title":"The Multi-Agent Pickup and Delivery Problem: MAPF, MARL and Its Warehouse Applications","created":"2022-03-14","cited_by_count":3,"area":null},{"id":"2206.08881","title":"Logic-based Reward Shaping for Multi-Agent Reinforcement Learning","created":"2022-06-17","cited_by_count":3,"area":null},{"id":"2208.01769","title":"Deep Reinforcement Learning for Multi-Agent Interaction","created":"2022-08-02","cited_by_count":3,"area":null},{"id":"2302.11793","title":"Revisiting the Gumbel-Softmax in MADDPG","created":"2023-02-23","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":"2505.05262","title":"Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration","created":"2025-05-08","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":"2510.18407","title":"Heterogeneous Adversarial Play in Interactive Environments","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2111.06614","title":"Collaboration Promotes Group Resilience in Multi-Agent RL","created":"2021-11-12","cited_by_count":2,"area":null},{"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":"2312.08468","title":"On Diagnostics for Understanding Agent Training Behaviour in Cooperative MARL","created":"2023-12-13","cited_by_count":2,"area":null},{"id":"2401.00132","title":"Contrastive learning-based agent modeling for deep reinforcement learning","created":"2023-12-30","cited_by_count":2,"area":null},{"id":"2402.14090","title":"Social Environment Design","created":"2024-02-21","cited_by_count":2,"area":null},{"id":"2501.15695","title":"Contextual Knowledge Sharing in Multi-Agent Reinforcement Learning with Decentralized Communication and Coordination","created":"2025-01-26","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":"2109.09034","title":"Greedy UnMixing for Q-Learning in Multi-Agent Reinforcement Learning","created":"2021-09-19","cited_by_count":1,"area":null},{"id":"2207.14443","title":"A Survey of Learning on Small Data: Generalization, Optimization, and Challenge","created":"2022-07-29","cited_by_count":1,"area":null},{"id":"2209.01054","title":"Taming Multi-Agent Reinforcement Learning with Estimator Variance Reduction","created":"2022-09-02","cited_by_count":1,"area":null},{"id":"2307.08024","title":"Bayesian inference for data-efficient, explainable, and safe robotic motion planning: A review","created":"2023-07-16","cited_by_count":1,"area":null},{"id":"2310.05053","title":"FP3O: Enabling Proximal Policy Optimization in Multi-Agent Cooperation with Parameter-Sharing Versatility","created":"2023-10-08","cited_by_count":1,"area":null},{"id":"2401.03504","title":"ClusterComm: Discrete Communication in Decentralized MARL using Internal Representation Clustering","created":"2024-01-07","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":"2507.18867","title":"Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning via Incorporating Generalized Human Expertise","created":"2025-07-25","cited_by_count":1,"area":null},{"id":"2508.02826","title":"TransAM: Transformer-Based Agent Modeling for Multi-Agent Systems via Local Trajectory Encoding","created":"2025-08-04","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":"2109.09038","title":"Regularize! Don't Mix: Multi-Agent Reinforcement Learning without Explicit Centralized Structures","created":"2021-09-19","cited_by_count":0,"area":null},{"id":"2201.01450","title":"Offsetting Unequal Competition through RL-assisted Incentive Schemes","created":"2022-01-05","cited_by_count":0,"area":null},{"id":"2201.12891","title":"Learning Collective Action under Risk Diversity","created":"2022-01-30","cited_by_count":0,"area":null},{"id":"2203.03021","title":"Hierarchically Structured Scheduling and Execution of Tasks in a Multi-Agent Environment","created":"2022-03-06","cited_by_count":0,"area":null},{"id":"2301.03887","title":"Actor-Director-Critic: A Novel Deep Reinforcement Learning Framework","created":"2023-01-10","cited_by_count":0,"area":null},{"id":"2302.09277","title":"Promoting Cooperation in Multi-Agent Reinforcement Learning via Mutual Help","created":"2023-02-18","cited_by_count":0,"area":null},{"id":"2305.05573","title":"An Algorithm For Adversary Aware Decentralized Networked MARL","created":"2023-05-09","cited_by_count":0,"area":null},{"id":"2312.12973","title":"Sparse Mean Field Load Balancing in Large Localized Queueing Systems","created":"2023-12-20","cited_by_count":0,"area":null},{"id":"2312.15412","title":"CARSS: Cooperative Attention-guided Reinforcement Subpath Synthesis for Solving Traveling Salesman Problem","created":"2023-12-24","cited_by_count":0,"area":null},{"id":"2404.13142","title":"Decentralized Coordination of Distributed Energy Resources through Local Energy Markets and Deep Reinforcement Learning","created":"2024-04-19","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":"2502.19297","title":"Combining Planning and Reinforcement Learning for Solving Relational Multiagent Domains","created":"2025-02-26","cited_by_count":0,"area":null},{"id":"2503.18816","title":"Learning Multi-Robot Coordination through Locality-Based Factorized Multi-Agent Actor-Critic Algorithm","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2505.09756","title":"LOD: Latent Objective Discovery in Heterogeneous Multi-Agent Reinforcement Learning","created":"2025-05-14","cited_by_count":0,"area":null},{"id":"2507.14553","title":"Clutter Detection and Removal by Multi-Objective Analysis for Photographic Guidance","created":"2025-07-19","cited_by_count":0,"area":null},{"id":"2507.18623","title":"Moving Out: Physically-grounded Human-AI Collaboration","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2507.20143","title":"Concept Learning for Cooperative Multi-Agent Reinforcement Learning","created":"2025-07-27","cited_by_count":0,"area":null},{"id":"2507.21631","title":"\"Teammates, Am I Clear?\": Analysing Legible Behaviours in Teams","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2507.22782","title":"Enhancing Multi-Agent Collaboration with Attention-Based Actor-Critic Policies","created":"2025-07-30","cited_by_count":0,"area":null},{"id":"2508.01049","title":"Centralized Adaptive Sampling for Reliable Co-Training of Independent Multi-Agent Policies","created":"2025-08-01","cited_by_count":0,"area":null},{"id":"2511.10409","title":"Explaining Decentralized Multi-Agent Reinforcement Learning Policies","created":"2025-11-13","cited_by_count":0,"area":null},{"id":"2601.21523","title":"Explicit Credit Assignment through Local Rewards and Dependence Graphs in Multi-Agent Reinforcement Learning","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.12520","title":"Multi-Agent Model-Based Reinforcement Learning with Joint State-Action Learned Embeddings","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2605.03842","title":"SOAR: Real-Time Joint Optimization of Order Allocation and Robot Scheduling in Robotic Mobile Fulfillment Systems","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.06557","title":"Coordination Matters: Evaluation of Cooperative Multi-Agent Reinforcement Learning","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.31318","title":"Generalized Intention Modeling in Multi-Agent Reinforcement Learning","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.14130","title":"Contract-Based Compositional Shielding for Safe Multi-Agent Reinforcement Learning","created":"2026-06-12","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":"2610.18808","title":"Optimizing Team Behavior via Extremum-seeking Control in Multi-agent Reinforcement Learning","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}