{"total":13,"rows":[{"id":"2111.06721","title":"Causal Multi-Agent Reinforcement Learning: Review and Open Problems","created":"2021-11-12","cited_by_count":16,"area":null},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"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":"2508.04811","title":"HCRide: Harmonizing Passenger Fairness and Driver Preference for Human-Centered Ride-Hailing","created":"2025-08-06","cited_by_count":7,"area":null},{"id":"2203.04749","title":"Bilateral Deep Reinforcement Learning Approach for Better-than-human Car Following Model","created":"2022-03-03","cited_by_count":4,"area":null},{"id":"2207.00978","title":"Renaissance Robot: Optimal Transport Policy Fusion for Learning Diverse Skills","created":"2022-07-03","cited_by_count":2,"area":null},{"id":"2203.09565","title":"Strategic Maneuver and Disruption with Reinforcement Learning Approaches for Multi-Agent Coordination","created":"2022-03-17","cited_by_count":1,"area":null},{"id":"2302.01471","title":"User-centric Heterogeneous-action Deep Reinforcement Learning for Virtual Reality in the Metaverse over Wireless Networks","created":"2023-02-03","cited_by_count":1,"area":null},{"id":"2311.06255","title":"Privacy-Engineered Value Decomposition Networks for Cooperative Multi-Agent Reinforcement Learning","created":"2023-09-13","cited_by_count":1,"area":null},{"id":"2212.07891","title":"Emergent Behaviors in Multi-Agent Target Acquisition","created":"2022-12-15","cited_by_count":0,"area":null},{"id":"2303.04349","title":"Virtual Reality in Metaverse over Wireless Networks with User-centered Deep Reinforcement Learning","created":"2023-03-08","cited_by_count":0,"area":null},{"id":"2409.00754","title":"Cooperative Path Planning with Asynchronous Multiagent Reinforcement Learning","created":"2024-09-01","cited_by_count":0,"area":null},{"id":"2609.16163","title":"GPEvac: GNN-Based PPO for Adaptive Evacuation Routing During Shooting Events","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}