{"total":15,"rows":[{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328,"area":"alignment"},{"id":"2401.04056","title":"A Minimaximalist Approach to Reinforcement Learning from Human Feedback","created":"2024-01-08","cited_by_count":144,"area":"alignment"},{"id":"2005.02575","title":"Active Preference-Based Gaussian Process Regression for Reward Learning","created":"2020-05-06","cited_by_count":71,"area":"alignment"},{"id":"2109.12750","title":"Learning Multimodal Rewards from Rankings","created":"2021-09-27","cited_by_count":41,"area":"alignment"},{"id":"2411.04625","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF","created":"2024-11-07","cited_by_count":33,"area":"alignment"},{"id":"2406.02764","title":"Adaptive Preference Scaling for Reinforcement Learning with Human Feedback","created":"2024-06-04","cited_by_count":20,"area":"alignment"},{"id":"2303.13512","title":"Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition","created":"2023-03-23","cited_by_count":15,"area":"alignment"},{"id":"2106.04316","title":"Exploration and preference satisfaction trade-off in reward-free learning","created":"2021-06-08","cited_by_count":12,"area":"alignment"},{"id":"2101.08937","title":"Prior Preference Learning from Experts:Designing a Reward with Active Inference","created":"2021-01-22","cited_by_count":8,"area":"alignment"},{"id":"2401.18040","title":"Enhancing End-to-End Multi-Task Dialogue Systems: A Study on Intrinsic Motivation Reinforcement Learning Algorithms for Improved Training and Adaptability","created":"2024-01-31","cited_by_count":6,"area":"alignment"},{"id":"2412.09104","title":"In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement Learning","created":"2024-12-12","cited_by_count":3,"area":"alignment"},{"id":"2302.08734","title":"A State Augmentation based approach to Reinforcement Learning from Human Preferences","created":"2023-02-17","cited_by_count":2,"area":"alignment"},{"id":"2307.05405","title":"Boosting Feedback Efficiency of Interactive Reinforcement Learning by Adaptive Learning from Scores","created":"2023-07-11","cited_by_count":1,"area":"alignment"},{"id":"2406.04838","title":"Algorithms for learning value-aligned policies considering admissibility relaxation","created":"2024-06-07","cited_by_count":1,"area":"alignment"},{"id":"1903.05216","title":"Learning Gaussian Policies from Corrective Human Feedback","created":"2019-03-12","cited_by_count":0,"area":"alignment"}],"next_cursor":null}