{"total":31,"rows":[{"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":"2304.08944","title":"Provably Feedback-Efficient Reinforcement Learning via Active Reward Learning","created":"2023-04-18","cited_by_count":15,"area":null},{"id":"2307.16348","title":"Rating-based Reinforcement Learning","created":"2023-07-30","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":"2206.05255","title":"Interactively Learning Preference Constraints in Linear Bandits","created":"2022-06-10","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":"2412.07207","title":"MAPLE: A Framework for Active Preference Learning Guided by Large Language Models","created":"2024-12-10","cited_by_count":6,"area":null},{"id":"2512.04453","title":"Open-Ended Goal Inference through Actions and Language for Human-Robot Collaboration","created":"2025-12-04","cited_by_count":5,"area":null},{"id":"2310.18601","title":"Online Decision Mediation","created":"2023-10-28","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":"2110.04192","title":"Explaining Reward Functions to Humans for Better Human-Robot Collaboration","created":"2021-10-08","cited_by_count":3,"area":null},{"id":"2406.14699","title":"Preferential Multi-Objective Bayesian Optimization","created":"2024-06-20","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":"2307.12158","title":"DIP-RL: Demonstration-Inferred Preference Learning in Minecraft","created":"2023-07-22","cited_by_count":2,"area":null},{"id":"2506.21887","title":"Interactive Multi-Objective Probabilistic Preference Learning with Soft and Hard Bounds","created":"2025-06-27","cited_by_count":2,"area":null},{"id":"2304.09803","title":"On the Perception of Difficulty: Differences between Humans and AI","created":"2023-04-19","cited_by_count":1,"area":null},{"id":"2306.08001","title":"A Markovian Formalism for Active Querying","created":"2023-06-13","cited_by_count":1,"area":null},{"id":"2308.08017","title":"Active Inverse Learning in Stackelberg Trajectory Games","created":"2023-08-15","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":"2403.06267","title":"FARPLS: A Feature-Augmented Robot Trajectory Preference Labeling System to Assist Human Labelers' Preference Elicitation","created":"2024-03-10","cited_by_count":1,"area":null},{"id":"2409.16577","title":"Reactive Multi-Robot Navigation in Outdoor Environments Through Uncertainty-Aware Active Learning of Human Preference Landscape","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2310.07389","title":"Learning a Reward Function for User-Preferred Appliance Scheduling","created":"2023-10-11","cited_by_count":0,"area":null},{"id":"2402.15997","title":"Cieran: Designing Sequential Colormaps via In-Situ Active Preference Learning","created":"2024-02-25","cited_by_count":0,"area":null},{"id":"2512.19057","title":"Efficient Personalization of Generative Models via Optimal Experimental Design","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2603.09011","title":"Improving through Interaction: Searching Behavioral Representation Spaces with CMA-ES-IG","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2604.07480","title":"Active Reward Machine Inference From Raw State Trajectories","created":"2026-04-08","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":"2608.11229","title":"Synchronizing Beliefs with Second-Order Theory-of-Mind in Human-Autonomy Teams (Extended Version)","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.02242","title":"Propose to Learn, Learn to Propose: Evaluability-Aware Assistance under Bounded Rationality","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.39055","title":"The Missing Coefficients: Bayesian Pairwise Merging for Model Personalization","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}