{"total":17,"rows":[{"id":"2306.00942","title":"Train Offline, Test Online: A Real Robot Learning Benchmark","created":"2023-06-01","cited_by_count":47,"area":null},{"id":"2405.19946","title":"Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf","created":"2024-05-30","cited_by_count":24,"area":null},{"id":"2206.03787","title":"Action Noise in Off-Policy Deep Reinforcement Learning: Impact on Exploration and Performance","created":"2022-06-08","cited_by_count":22,"area":null},{"id":"2305.15284","title":"Replicable Reinforcement Learning","created":"2023-05-24","cited_by_count":21,"area":null},{"id":"2311.18207","title":"Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation","created":"2023-11-30","cited_by_count":13,"area":null},{"id":"2312.03814","title":"Pearl: A Production-ready Reinforcement Learning Agent","created":"2023-12-06","cited_by_count":9,"area":null},{"id":"2301.08940","title":"Quasi-optimal Reinforcement Learning with Continuous Actions","created":"2023-01-21","cited_by_count":7,"area":null},{"id":"2312.16248","title":"XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library","created":"2023-12-25","cited_by_count":5,"area":null},{"id":"2303.10180","title":"Towards Real-World Applications of Personalized Anesthesia Using Policy Constraint Q Learning for Propofol Infusion Control","created":"2023-03-17","cited_by_count":2,"area":null},{"id":"2505.10861","title":"Improving the Data-efficiency of Reinforcement Learning by Warm-starting with LLM","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2310.15333","title":"Safe and Interpretable Estimation of Optimal Treatment Regimes","created":"2023-10-23","cited_by_count":1,"area":null},{"id":"2311.04397","title":"ToP-ToM: Trust-aware Robot Policy with Theory of Mind","created":"2023-11-07","cited_by_count":1,"area":null},{"id":"2504.18235","title":"BiasBench: A reproducible benchmark for tuning the biases of event cameras","created":"2025-04-25","cited_by_count":1,"area":null},{"id":"2311.01749","title":"Epidemic Decision-making System Based Federated Reinforcement Learning","created":"2023-11-03","cited_by_count":0,"area":null},{"id":"2508.02581","title":"Automated Construction of Artificial Lattice Structures with Designer Electronic States","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2605.06564","title":"Dynamic Treatment on Networks","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2608.10050","title":"Observational Policy Ranking for SMB Financial Guidance from Multi-Action Accounting Logs","created":"2026-08-10","cited_by_count":0,"area":null}],"next_cursor":null}