{"total":20,"rows":[{"id":"2101.08001","title":"UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers","created":"2021-01-20","cited_by_count":39,"area":null},{"id":"2304.09853","title":"Bridging RL Theory and Practice with the Effective Horizon","created":"2023-04-19","cited_by_count":31,"area":null},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2212.03830","title":"A Hierarchical Deep Reinforcement Learning Framework for 6-DOF UCAV Air-to-Air Combat","created":"2022-12-05","cited_by_count":10,"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":"2202.09644","title":"Multi-task Safe Reinforcement Learning for Navigating Intersections in Dense Traffic","created":"2022-02-19","cited_by_count":8,"area":null},{"id":"2105.14780","title":"Procedural Content Generation: Better Benchmarks for Transfer Reinforcement Learning","created":"2021-05-31","cited_by_count":7,"area":null},{"id":"2103.00683","title":"Decision Making in Monopoly using a Hybrid Deep Reinforcement Learning Approach","created":"2021-03-01","cited_by_count":6,"area":null},{"id":"2203.10941","title":"Transfer Dynamics in Emergent Evolutionary Curricula","created":"2022-03-03","cited_by_count":6,"area":null},{"id":"2207.01251","title":"Asynchronous Curriculum Experience Replay: A Deep Reinforcement Learning Approach for UAV Autonomous Motion Control in Unknown Dynamic Environments","created":"2022-07-04","cited_by_count":4,"area":null},{"id":"2312.03764","title":"Similarity-based Knowledge Transfer for Cross-Domain Reinforcement Learning","created":"2023-12-05","cited_by_count":4,"area":null},{"id":"2408.13567","title":"Hybrid Training for Enhanced Multi-task Generalization in Multi-agent Reinforcement Learning","created":"2024-08-24","cited_by_count":3,"area":null},{"id":"2107.09807","title":"Improved Reinforcement Learning in Cooperative Multi-agent Environments Using Knowledge Transfer","created":"2021-07-20","cited_by_count":1,"area":null},{"id":"2209.06904","title":"Forecasting Evolution of Clusters in Game Agents with Hebbian Learning","created":"2022-08-19","cited_by_count":1,"area":null},{"id":"2402.08184","title":"Enabling Multi-Agent Transfer Reinforcement Learning via Scenario Independent Representation","created":"2024-02-13","cited_by_count":1,"area":null},{"id":"2108.02323","title":"Active Reinforcement Learning over MDPs","created":"2021-08-05","cited_by_count":0,"area":null},{"id":"2310.00964","title":"All by Myself: Learning Individualized Competitive Behaviour with a Contrastive Reinforcement Learning optimization","created":"2023-10-02","cited_by_count":0,"area":null},{"id":"2402.00738","title":"FM3Q: Factorized Multi-Agent MiniMax Q-Learning for Two-Team Zero-Sum Markov Game","created":"2024-02-01","cited_by_count":0,"area":null},{"id":"2506.10384","title":"NeuroPAL: Punctuated Anytime Learning with Neuroevolution for Macromanagement in Starcraft: Brood War","created":"2025-06-12","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}],"next_cursor":null}