{"total":73,"rows":[{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"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":"2309.02473","title":"A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges","created":"2023-09-05","cited_by_count":148,"area":"offlinerl"},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2109.08273","title":"ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning","created":"2021-09-17","cited_by_count":108,"area":"offlinerl"},{"id":"2310.13639","title":"Contrastive Preference Learning: Learning from Human Feedback without RL","created":"2023-10-20","cited_by_count":79,"area":"alignment"},{"id":"2305.15363","title":"Inverse Preference Learning: Preference-based RL without a Reward Function","created":"2023-05-24","cited_by_count":68,"area":"alignment"},{"id":"2106.12177","title":"Imitation Learning: Progress, Taxonomies and Challenges","created":"2021-06-23","cited_by_count":58,"area":"offlinerl"},{"id":"2301.01392","title":"Benchmarks and Algorithms for Offline Preference-Based Reward Learning","created":"2023-01-03","cited_by_count":56,"area":"alignment"},{"id":"2206.02231","title":"Models of human preference for learning reward functions","created":"2022-06-05","cited_by_count":54,"area":"alignment"},{"id":"2204.06601","title":"Causal Confusion and Reward Misidentification in Preference-Based Reward Learning","created":"2022-04-13","cited_by_count":53,"area":"alignment"},{"id":"2104.00053","title":"LazyDAgger: Reducing Context Switching in Interactive Imitation Learning","created":"2021-03-31","cited_by_count":51,"area":"offlinerl"},{"id":"2103.04529","title":"Self-Supervised Online Reward Shaping in Sparse-Reward Environments","created":"2021-03-08","cited_by_count":37,"area":null},{"id":"2107.10939","title":"What are you optimizing for? Aligning Recommender Systems with Human Values","created":"2021-07-22","cited_by_count":29,"area":"alignment"},{"id":"2007.12315","title":"Bayesian Robust Optimization for Imitation Learning","created":"2020-07-24","cited_by_count":28,"area":"offlinerl"},{"id":"2010.10181","title":"Robust Imitation Learning from Noisy Demonstrations","created":"2020-10-20","cited_by_count":26,"area":"offlinerl"},{"id":"2208.10687","title":"The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Types","created":"2022-08-23","cited_by_count":26,"area":"alignment"},{"id":"2209.10968","title":"Proximal Point Imitation Learning","created":"2022-09-22","cited_by_count":26,"area":"offlinerl"},{"id":"2408.03029","title":"Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning","created":"2024-08-06","cited_by_count":22,"area":"deeprl"},{"id":"2301.04741","title":"Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models","created":"2023-01-11","cited_by_count":21,"area":null},{"id":"2202.03481","title":"A Ranking Game for Imitation Learning","created":"2022-02-07","cited_by_count":18,"area":"offlinerl"},{"id":"2107.09251","title":"Offline Preference-Based Apprenticeship Learning","created":"2021-07-20","cited_by_count":17,"area":"offlinerl"},{"id":"2201.07082","title":"Inducing Structure in Reward Learning by Learning Features","created":"2022-01-18","cited_by_count":16,"area":null},{"id":"2209.10974","title":"Identifiability and generalizability from multiple experts in Inverse Reinforcement Learning","created":"2022-09-22","cited_by_count":16,"area":"offlinerl"},{"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":"2310.07932","title":"What Matters to You? Towards Visual Representation Alignment for Robot Learning","created":"2023-10-11","cited_by_count":14,"area":"alignment"},{"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":"2106.06499","title":"Policy Gradient Bayesian Robust Optimization for Imitation Learning","created":"2021-06-11","cited_by_count":11,"area":"offlinerl"},{"id":"2302.01928","title":"Aligning Robot and Human Representations","created":"2023-02-03","cited_by_count":11,"area":null},{"id":"2112.14004","title":"Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations","created":"2021-12-28","cited_by_count":10,"area":"offlinerl"},{"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":"2402.17975","title":"Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards","created":"2024-02-28","cited_by_count":9,"area":"alignment"},{"id":"2406.15599","title":"Pareto-Optimal Learning from Preferences with Hidden Context","created":"2024-06-21","cited_by_count":8,"area":"alignment"},{"id":"2412.02818","title":"RoboMD: Uncovering Robot Vulnerabilities through Semantic Potential Fields","created":"2024-12-03","cited_by_count":7,"area":"deeprl"},{"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":"2511.14565","title":"Masked IRL: LLM-Guided Reward Disambiguation from Demonstrations and Language","created":"2025-11-18","cited_by_count":4,"area":"alignment"},{"id":"2212.02753","title":"Safe Inverse Reinforcement Learning via Control Barrier Function","created":"2022-12-06","cited_by_count":3,"area":"offlinerl"},{"id":"2406.18450","title":"Preference Elicitation for Offline Reinforcement Learning","created":"2024-06-26","cited_by_count":3,"area":"offlinerl"},{"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":"2203.01696","title":"Fail-Safe Adversarial Generative Imitation Learning","created":"2022-03-03","cited_by_count":2,"area":"offlinerl"},{"id":"2203.04951","title":"Learning from Physical Human Feedback: An Object-Centric One-Shot Adaptation Method","created":"2022-03-09","cited_by_count":2,"area":"alignment"},{"id":"2307.12158","title":"DIP-RL: Demonstration-Inferred Preference Learning in Minecraft","created":"2023-07-22","cited_by_count":2,"area":null},{"id":"2310.15694","title":"COPR: Continual Learning Human Preference through Optimal Policy Regularization","created":"2023-10-24","cited_by_count":2,"area":"alignment"},{"id":"2407.06459","title":"How Much Progress Did I Make? An Unexplored Human Feedback Signal for Teaching Robots","created":"2024-07-08","cited_by_count":2,"area":"alignment"},{"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":"2211.15542","title":"Autonomous Assessment of Demonstration Sufficiency via Bayesian Inverse Reinforcement Learning","created":"2022-11-28","cited_by_count":1,"area":"offlinerl"},{"id":"2411.11182","title":"Improving User Experience in Preference-Based Optimization of Reward Functions for Assistive Robots","created":"2024-11-17","cited_by_count":1,"area":"alignment"},{"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":"2205.07882","title":"Aligning Robot Representations with Humans","created":"2022-05-15","cited_by_count":0,"area":"alignment"},{"id":"2302.03586","title":"Adaptive Aggregation for Safety-Critical Control","created":"2023-02-07","cited_by_count":0,"area":null},{"id":"2303.06827","title":"Kernel Density Bayesian Inverse Reinforcement Learning","created":"2023-03-13","cited_by_count":0,"area":"offlinerl"},{"id":"2303.07846","title":"Sample-efficient Adversarial Imitation Learning","created":"2023-03-14","cited_by_count":0,"area":"offlinerl"},{"id":"2405.17047","title":"Interpretable Robotic Manipulation from Language","created":"2024-05-27","cited_by_count":0,"area":null},{"id":"2412.07990","title":"Adaptive Querying for Reward Learning from Human Feedback","created":"2024-12-11","cited_by_count":0,"area":"alignment"},{"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":"2505.12327","title":"Robust Planning for Autonomous Driving via Mixed Adversarial Diffusion Predictions","created":"2025-05-18","cited_by_count":0,"area":"diffusion"},{"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":"2605.12831","title":"Quantifying Potential Observation Missingness in Inverse Reinforcement Learning","created":"2026-05-12","cited_by_count":0,"area":"offlinerl"},{"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},{"id":"2609.04066","title":"Subspace Inference Enables Efficient Active Reward Learning from Preferences","created":"2026-09-03","cited_by_count":0,"area":"alignment"},{"id":"2609.31855","title":"PHIRL: Aligning Learned Rewards with Task Progress for Inverse Reinforcement Learning","created":"2026-09-25","cited_by_count":0,"area":"alignment"}],"next_cursor":null}