{"total":30,"rows":[{"id":"2111.03026","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","created":"2021-11-04","cited_by_count":106,"area":null},{"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":"2405.07162","title":"Learning Reward for Robot Skills Using Large Language Models via Self-Alignment","created":"2024-05-12","cited_by_count":20,"area":null},{"id":"2404.13895","title":"Optimal Design for Human Preference Elicitation","created":"2024-04-22","cited_by_count":17,"area":null},{"id":"2304.08944","title":"Provably Feedback-Efficient Reinforcement Learning via Active Reward Learning","created":"2023-04-18","cited_by_count":15,"area":null},{"id":"2305.17400","title":"Query-Policy Misalignment in Preference-Based Reinforcement Learning","created":"2023-05-27","cited_by_count":15,"area":null},{"id":"2108.07259","title":"APReL: A Library for Active Preference-based Reward Learning Algorithms","created":"2021-08-16","cited_by_count":14,"area":null},{"id":"2107.05825","title":"Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks","created":"2021-07-13","cited_by_count":13,"area":null},{"id":"2405.03164","title":"The Role of Predictive Uncertainty and Diversity in Embodied AI and Robot Learning","created":"2024-05-06","cited_by_count":11,"area":null},{"id":"2105.01850","title":"Preference learning along multiple criteria: A game-theoretic perspective","created":"2021-05-05","cited_by_count":9,"area":null},{"id":"2402.15757","title":"Batch Active Learning of Reward Functions from Human Preferences","created":"2024-02-24","cited_by_count":8,"area":null},{"id":"2405.06424","title":"Improving Instruction Following in Language Models through Proxy-Based Uncertainty Estimation","created":"2024-05-10","cited_by_count":6,"area":null},{"id":"2308.04571","title":"Optimizing Algorithms From Pairwise User Preferences","created":"2023-08-08","cited_by_count":4,"area":null},{"id":"2106.04678","title":"Incentivizing Efficient Equilibria in Traffic Networks with Mixed Autonomy","created":"2021-05-06","cited_by_count":3,"area":null},{"id":"2309.02632","title":"Deep Reinforcement Learning from Hierarchical Preference Design","created":"2023-09-06","cited_by_count":3,"area":null},{"id":"2311.02085","title":"Preference Elicitation with Soft Attributes in Interactive Recommendation","created":"2023-10-22","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":"2211.13260","title":"Actively Learning Costly Reward Functions for Reinforcement Learning","created":"2022-11-23","cited_by_count":2,"area":null},{"id":"2306.04925","title":"Prefer to Classify: Improving Text Classifiers via Auxiliary Preference Learning","created":"2023-06-08","cited_by_count":2,"area":null},{"id":"2409.11535","title":"Balancing Optimality and Diversity: Human-Centered Decision Making through Generative Curation","created":"2024-09-17","cited_by_count":2,"area":null},{"id":"2608.15050","title":"Online Convex Optimization with Dueling Feedback","created":"2026-08-15","cited_by_count":2,"area":null},{"id":"2307.09692","title":"STRAPPER: Preference-based Reinforcement Learning via Self-training Augmentation and Peer Regularization","created":"2023-07-19","cited_by_count":1,"area":null},{"id":"2403.06003","title":"A Generalized Acquisition Function for Preference-based Reward Learning","created":"2024-03-09","cited_by_count":1,"area":null},{"id":"2306.06296","title":"Response Time Improves Choice Prediction and Function Estimation for Gaussian Process Models of Perception and Preferences","created":"2023-06-09","cited_by_count":0,"area":null},{"id":"2403.10160","title":"Online Policy Learning from Offline Preferences","created":"2024-03-15","cited_by_count":0,"area":null},{"id":"2411.01866","title":"Improving Trust Estimation in Human-Robot Collaboration Using Beta Reputation at Fine-grained Timescales","created":"2024-11-04","cited_by_count":0,"area":null},{"id":"2603.23777","title":"Human-in-the-Loop Pareto Optimization: Trade-off Characterization for Assist-as-Needed Training and Performance Evaluation","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2604.20210","title":"Vibrotactile Preference Learning: Uncertainty-Aware Preference Learning for Personalized Vibration Feedback","created":"2026-04-22","cited_by_count":0,"area":null}],"next_cursor":null}