{"total":19,"rows":[{"id":"2212.03363","title":"Few-Shot Preference Learning for Human-in-the-Loop RL","created":"2022-12-06","cited_by_count":87,"area":null},{"id":"2110.00284","title":"Learning Reward Functions from Scale Feedback","created":"2021-10-01","cited_by_count":24,"area":null},{"id":"2301.04741","title":"Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models","created":"2023-01-11","cited_by_count":21,"area":null},{"id":"2206.09670","title":"Benchmarking Constraint Inference in Inverse Reinforcement Learning","created":"2022-06-20","cited_by_count":18,"area":null},{"id":"2309.03315","title":"Robotic Table Tennis: A Case Study into a High Speed Learning System","created":"2023-09-06","cited_by_count":13,"area":null},{"id":"2310.08549","title":"Cross-Episodic Curriculum for Transformer Agents","created":"2023-10-12","cited_by_count":10,"area":null},{"id":"2507.19975","title":"A roadmap for AI in robotics","created":"2025-07-26","cited_by_count":7,"area":null},{"id":"2306.11168","title":"Learning Models of Adversarial Agent Behavior under Partial Observability","created":"2023-06-19","cited_by_count":5,"area":null},{"id":"2310.14092","title":"Learning Reward for Physical Skills using Large Language Model","created":"2023-10-21","cited_by_count":5,"area":null},{"id":"2101.07140","title":"Natural Language Specification of Reinforcement Learning Policies through Differentiable Decision Trees","created":"2021-01-18","cited_by_count":4,"area":null},{"id":"2212.01509","title":"Reinforcement learning with Demonstrations from Mismatched Task under Sparse Reward","created":"2022-12-03","cited_by_count":4,"area":null},{"id":"2310.07838","title":"Towards the Fundamental Limits of Knowledge Transfer over Finite Domains","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2401.17185","title":"Multi-Camera Asynchronous Ball Localization and Trajectory Prediction with Factor Graphs and Human Poses","created":"2024-01-30","cited_by_count":4,"area":null},{"id":"2405.03735","title":"Select to Perfect: Imitating desired behavior from large multi-agent data","created":"2024-05-06","cited_by_count":4,"area":null},{"id":"2109.07788","title":"Marginal MAP Estimation for Inverse RL under Occlusion with Observer Noise","created":"2021-09-16","cited_by_count":3,"area":null},{"id":"2501.01367","title":"Contrastive Learning from Exploratory Actions: Leveraging Natural Interactions for Preference Elicitation","created":"2025-01-02","cited_by_count":3,"area":null},{"id":"2107.02912","title":"Supervised Bayesian Specification Inference from Demonstrations","created":"2021-07-06","cited_by_count":1,"area":null},{"id":"2311.05084","title":"Signal Temporal Logic-Guided Apprenticeship Learning","created":"2023-11-09","cited_by_count":1,"area":null},{"id":"2502.18447","title":"Supervised Reward Inference","created":"2025-02-25","cited_by_count":0,"area":null}],"next_cursor":null}