{"total":17,"rows":[{"id":"2110.00284","title":"Learning Reward Functions from Scale Feedback","created":"2021-10-01","cited_by_count":24,"area":null},{"id":"2203.04272","title":"Policy-Based Bayesian Experimental Design for Non-Differentiable Implicit Models","created":"2022-03-08","cited_by_count":16,"area":null},{"id":"2402.05367","title":"Principled Preferential Bayesian Optimization","created":"2024-02-08","cited_by_count":16,"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":"2301.00810","title":"SIRL: Similarity-based Implicit Representation Learning","created":"2023-01-02","cited_by_count":14,"area":null},{"id":"2301.00901","title":"Towards Modeling and Influencing the Dynamics of Human Learning","created":"2023-01-02","cited_by_count":11,"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":"2503.00924","title":"PABBO: Preferential Amortized Black-Box Optimization","created":"2025-03-02","cited_by_count":8,"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":"2403.06003","title":"A Generalized Acquisition Function for Preference-based Reward Learning","created":"2024-03-09","cited_by_count":1,"area":null},{"id":"2403.15045","title":"DP-Dueling: Learning from Preference Feedback without Compromising User Privacy","created":"2024-03-22","cited_by_count":1,"area":null},{"id":"2601.22335","title":"Knowledge Gradient for Preference Learning","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2205.09151","title":"An Approach to Investigate Public Opinion, Views, and Perspectives Towards Exoskeleton Technology","created":"2022-04-27","cited_by_count":0,"area":null},{"id":"2310.00750","title":"Identifying Copeland Winners in Dueling Bandits with Indifferences","created":"2023-10-01","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":"2605.26072","title":"Active Query Synthesis for Preference Learning","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2609.28427","title":"Context-Continuous Preference Learning for Exoskeleton Personalization","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}