{"total":30,"rows":[{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2103.04529","title":"Self-Supervised Online Reward Shaping in Sparse-Reward Environments","created":"2021-03-08","cited_by_count":37,"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":"2201.07082","title":"Inducing Structure in Reward Learning by Learning Features","created":"2022-01-18","cited_by_count":16,"area":null},{"id":"2307.16348","title":"Rating-based Reinforcement Learning","created":"2023-07-30","cited_by_count":15,"area":null},{"id":"2301.00810","title":"SIRL: Similarity-based Implicit Representation Learning","created":"2023-01-02","cited_by_count":14,"area":null},{"id":"2109.10312","title":"Example-Driven Model-Based Reinforcement Learning for Solving Long-Horizon Visuomotor Tasks","created":"2021-09-21","cited_by_count":13,"area":null},{"id":"2107.06317","title":"Inverse Contextual Bandits: Learning How Behavior Evolves over Time","created":"2021-07-13","cited_by_count":12,"area":null},{"id":"2302.01928","title":"Aligning Robot and Human Representations","created":"2023-02-03","cited_by_count":11,"area":null},{"id":"2310.03023","title":"Human-oriented Representation Learning for Robotic Manipulation","created":"2023-10-04","cited_by_count":10,"area":null},{"id":"2310.18591","title":"Inverse Decision Modeling: Learning Interpretable Representations of Behavior","created":"2023-10-28","cited_by_count":10,"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":"2111.03936","title":"SOPE: Spectrum of Off-Policy Estimators","created":"2021-11-06","cited_by_count":5,"area":null},{"id":"2306.08803","title":"Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning","created":"2023-06-15","cited_by_count":5,"area":null},{"id":"2106.05402","title":"Deception in Social Learning: A Multi-Agent Reinforcement Learning Perspective","created":"2021-06-09","cited_by_count":4,"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":"2202.08444","title":"A Survey on Deep Reinforcement Learning-based Approaches for Adaptation and Generalization","created":"2022-02-17","cited_by_count":1,"area":null},{"id":"2502.03717","title":"Efficiently Generating Expressive Quadruped Behaviors via Language-Guided Preference Learning","created":"2025-02-06","cited_by_count":1,"area":null},{"id":"2606.29201","title":"Behavior Uncloning: Distilling Mode Redirection into Policy Weights without Inference-Time Steering","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2101.01366","title":"A Symmetric Loss Perspective of Reliable Machine Learning","created":"2021-01-05","cited_by_count":0,"area":null},{"id":"2111.14324","title":"Is the Rush to Machine Learning Jeopardizing Safety? Results of a Survey","created":"2021-11-29","cited_by_count":0,"area":null},{"id":"2302.03586","title":"Adaptive Aggregation for Safety-Critical Control","created":"2023-02-07","cited_by_count":0,"area":null},{"id":"2405.17047","title":"Interpretable Robotic Manipulation from Language","created":"2024-05-27","cited_by_count":0,"area":null},{"id":"2502.10476","title":"Multi-Objective Planning with Contextual Lexicographic Reward Preferences","created":"2025-02-13","cited_by_count":0,"area":null},{"id":"2502.18447","title":"Supervised Reward Inference","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2602.15206","title":"MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference","created":"2026-02-16","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":"2605.22986","title":"Robots That Know What to Ask: Recovering Misaligned Rewards through Targeted Explanations","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2607.27630","title":"SCOPE: Synthetic Conditional Objectives for Policy Evolution in Black-Box Combinatorial Optimization","created":"2026-07-30","cited_by_count":0,"area":null}],"next_cursor":null}