{"total":71,"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":"2106.02195","title":"Celebrating Diversity in Shared Multi-Agent Reinforcement Learning","created":"2021-06-04","cited_by_count":98,"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":"2406.14558","title":"CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics","created":"2024-06-20","cited_by_count":44,"area":null},{"id":"2301.07137","title":"Heterogeneous Multi-Robot Reinforcement Learning","created":"2023-01-17","cited_by_count":36,"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":"2210.12566","title":"Solving Continuous Control via Q-learning","created":"2022-10-22","cited_by_count":24,"area":null},{"id":"2211.12712","title":"Contrastive Identity-Aware Learning for Multi-Agent Value Decomposition","created":"2022-11-23","cited_by_count":19,"area":null},{"id":"2207.14138","title":"Generating Teammates for Training Robust Ad Hoc Teamwork Agents via Best-Response Diversity","created":"2022-07-28","cited_by_count":17,"area":null},{"id":"2205.02561","title":"LDSA: Learning Dynamic Subtask Assignment in Cooperative Multi-Agent Reinforcement Learning","created":"2022-05-05","cited_by_count":15,"area":null},{"id":"2305.05909","title":"Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers","created":"2023-05-10","cited_by_count":15,"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":"2303.00912","title":"Parameter Sharing with Network Pruning for Scalable Multi-Agent Deep Reinforcement Learning","created":"2023-03-02","cited_by_count":14,"area":null},{"id":"2305.02128","title":"System Neural Diversity: Measuring Behavioral Heterogeneity in Multi-Agent Learning","created":"2023-05-03","cited_by_count":14,"area":null},{"id":"2207.05683","title":"Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL","created":"2022-06-01","cited_by_count":11,"area":null},{"id":"2305.13937","title":"Multi-agent Continual Coordination via Progressive Task Contextualization","created":"2023-05-07","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":"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":"2410.01706","title":"Sable: a Performant, Efficient and Scalable Sequence Model for MARL","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2307.16186","title":"ESP: Exploiting Symmetry Prior for Multi-Agent Reinforcement Learning","created":"2023-07-30","cited_by_count":9,"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":"2312.09009","title":"Adaptive parameter sharing for multi-agent reinforcement learning","created":"2023-12-14","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":"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":"2410.08540","title":"Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning","created":"2024-10-11","cited_by_count":6,"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":"2305.09458","title":"An Empirical Study on Google Research Football Multi-agent Scenarios","created":"2023-05-16","cited_by_count":5,"area":null},{"id":"2306.17411","title":"Decentralized Motor Skill Learning for Complex Robotic Systems","created":"2023-06-30","cited_by_count":4,"area":null},{"id":"2410.07287","title":"Crafting Desirable Climate Trajectories with RL Explored Socio-Environmental Simulations","created":"2024-10-09","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":"2206.09046","title":"Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis","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":"2305.13936","title":"Robust Multi-agent Communication via Multi-view Message Certification","created":"2023-05-07","cited_by_count":3,"area":null},{"id":"2401.15059","title":"Fully Independent Communication in Multi-Agent Reinforcement Learning","created":"2024-01-26","cited_by_count":3,"area":null},{"id":"2501.06058","title":"Capability-Aware Shared Hypernetworks for Flexible Heterogeneous Multi-Robot Coordination","created":"2025-01-10","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":"2306.11846","title":"Discovering Causality for Efficient Cooperation in Multi-Agent Environments","created":"2023-06-20","cited_by_count":2,"area":null},{"id":"2409.02246","title":"Multi-Agent Reinforcement Learning for Joint Police Patrol and Dispatch","created":"2024-09-03","cited_by_count":2,"area":null},{"id":"2503.01440","title":"Trajectory-Class-Aware Multi-Agent Reinforcement Learning","created":"2025-03-03","cited_by_count":2,"area":null},{"id":"2506.09434","title":"When Is Diversity Rewarded in Cooperative Multi-Agent Learning?","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2508.20315","title":"Multi-Agent Reinforcement Learning in Intelligent Transportation Systems: A Comprehensive Survey","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2304.05632","title":"Multi-agent Policy Reciprocity with Theoretical Guarantee","created":"2023-04-12","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":"2403.10112","title":"Evasive Active Hypothesis Testing with Deep Neuroevolution: The Single- and Multi-Agent Cases","created":"2024-03-15","cited_by_count":1,"area":null},{"id":"2406.17425","title":"CuDA2: An approach for Incorporating Traitor Agents into Cooperative Multi-Agent Systems","created":"2024-06-25","cited_by_count":1,"area":null},{"id":"2409.19391","title":"Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training","created":"2024-09-28","cited_by_count":1,"area":null},{"id":"2507.20377","title":"Multi-Agent Reinforcement Learning for Dynamic Mobility Resource Allocation with Hierarchical Adaptive Grouping","created":"2025-07-27","cited_by_count":1,"area":null},{"id":"2509.16709","title":"HypeMARL: Multi-Agent Reinforcement Learning For High-Dimensional, Parametric, and Distributed Systems","created":"2025-09-20","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":"2605.12388","title":"Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning","created":"2026-05-12","cited_by_count":1,"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":"2203.07832","title":"Learning to Infer Belief Embedded Communication","created":"2022-03-15","cited_by_count":0,"area":null},{"id":"2212.13379","title":"Learning Individual Policies in Large Multi-agent Systems through Local Variance Minimization","created":"2022-12-27","cited_by_count":0,"area":null},{"id":"2310.10948","title":"Combat Urban Congestion via Collaboration: Heterogeneous GNN-based MARL for Coordinated Platooning and Traffic Signal Control","created":"2023-10-17","cited_by_count":0,"area":null},{"id":"2403.06750","title":"Generalising Multi-Agent Cooperation through Task-Agnostic Communication","created":"2024-03-11","cited_by_count":0,"area":null},{"id":"2404.03101","title":"MARL-LNS: Cooperative Multi-agent Reinforcement Learning via Large Neighborhoods Search","created":"2024-04-03","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":"2505.09756","title":"LOD: Latent Objective Discovery in Heterogeneous Multi-Agent Reinforcement Learning","created":"2025-05-14","cited_by_count":0,"area":null},{"id":"2506.12453","title":"Topology-Assisted Spatio-Temporal Pattern Disentangling for Scalable MARL in Large-scale Autonomous Traffic Control","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2507.21638","title":"Assistax: A Multi-Agent Hardware-Accelerated Reinforcement Learning Benchmark for Assistive Robotics","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2508.15764","title":"Distributed Detection of Adversarial Attacks in Multi-Agent Reinforcement Learning with Continuous Action Space","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2603.04833","title":"SCoUT: Scalable Communication via Utility-Guided Temporal Grouping in Multi-Agent Reinforcement Learning","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.06977","title":"NePPO: Near-Potential Policy Optimization for General-Sum Multi-Agent Reinforcement Learning","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2603.15054","title":"Interference-Aware K-Step Reachable Communication in Multi-Agent Reinforcement Learning","created":"2026-03-16","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":"2607.09422","title":"Action-Factored Multi-Agent Reinforcement Learning for Scalable Quantum Device Tuning","created":"2026-07-10","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}