{"total":5,"rows":[{"id":"2306.08649","title":"OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments","created":"2023-06-14","cited_by_count":30,"area":null},{"id":"2306.16688","title":"SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores","created":"2023-06-29","cited_by_count":10,"area":null},{"id":"2305.16877","title":"Distributional Reinforcement Learning with Dual Expectile-Quantile Regression","created":"2023-05-26","cited_by_count":1,"area":null},{"id":"2507.00451","title":"Best Agent Identification for General Game Playing","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2508.18258","title":"ANO : Faster is Better in Noisy Landscape","created":"2025-08-25","cited_by_count":1,"area":null}],"next_cursor":null}