{"total":71,"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":"2106.05091","title":"PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training","created":"2021-06-09","cited_by_count":302,"area":"alignment"},{"id":"2402.03681","title":"RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback","created":"2024-02-06","cited_by_count":156,"area":"mllm"},{"id":"2401.04056","title":"A Minimaximalist Approach to Reinforcement Learning from Human Feedback","created":"2024-01-08","cited_by_count":144,"area":"alignment"},{"id":"2310.07899","title":"RoboCLIP: One Demonstration is Enough to Learn Robot Policies","created":"2023-10-11","cited_by_count":134,"area":"offlinerl"},{"id":"2111.03026","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","created":"2021-11-04","cited_by_count":106,"area":null},{"id":"2203.10050","title":"SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning","created":"2022-03-18","cited_by_count":97,"area":"alignment"},{"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":"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":"2205.12401","title":"Reward Uncertainty for Exploration in Preference-based Reinforcement Learning","created":"2022-05-24","cited_by_count":61,"area":"alignment"},{"id":"2603.02115","title":"Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons","created":"2026-03-02","cited_by_count":60,"area":"alignment"},{"id":"2504.12328","title":"A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future","created":"2025-04-12","cited_by_count":53,"area":"alignment"},{"id":"2405.14758","title":"Axioms for AI Alignment from Human Feedback","created":"2024-05-23","cited_by_count":52,"area":"alignment"},{"id":"2109.12750","title":"Learning Multimodal Rewards from Rankings","created":"2021-09-27","cited_by_count":41,"area":"alignment"},{"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":"2410.17055","title":"Optimal Design for Reward Modeling in RLHF","created":"2024-10-22","cited_by_count":25,"area":"alignment"},{"id":"2102.12466","title":"Information Directed Reward Learning for Reinforcement Learning","created":"2021-02-24","cited_by_count":24,"area":"alignment"},{"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":"2302.13507","title":"Active Reward Learning from Online Preferences","created":"2023-02-27","cited_by_count":13,"area":"alignment"},{"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":"2103.02727","title":"Preference-based Learning of Reward Function Features","created":"2021-03-03","cited_by_count":9,"area":"alignment"},{"id":"2105.01850","title":"Preference learning along multiple criteria: A game-theoretic perspective","created":"2021-05-05","cited_by_count":9,"area":null},{"id":"2402.17975","title":"Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards","created":"2024-02-28","cited_by_count":9,"area":"alignment"},{"id":"2402.15757","title":"Batch Active Learning of Reward Functions from Human Preferences","created":"2024-02-24","cited_by_count":8,"area":null},{"id":"2407.17482","title":"Reinforcement Learning from Human Feedback: Whose Culture, Whose Values, Whose Perspectives?","created":"2024-07-02","cited_by_count":8,"area":"alignment"},{"id":"2410.11584","title":"DeformPAM: Data-Efficient Learning for Long-horizon Deformable Object Manipulation via Preference-based Action Alignment","created":"2024-10-15","cited_by_count":7,"area":"alignment"},{"id":"2505.06079","title":"TREND: Tri-teaching for Robust Preference-based Reinforcement Learning with Demonstrations","created":"2025-05-09","cited_by_count":7,"area":"alignment"},{"id":"2405.00746","title":"Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning","created":"2024-04-30","cited_by_count":6,"area":"deeprl"},{"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":"2510.20264","title":"Optimistic Task Inference for Behavior Foundation Models","created":"2025-10-23","cited_by_count":6,"area":"deeprl"},{"id":"2211.06527","title":"Rewards Encoding Environment Dynamics Improves Preference-based Reinforcement Learning","created":"2022-11-12","cited_by_count":4,"area":"alignment"},{"id":"2308.04571","title":"Optimizing Algorithms From Pairwise User Preferences","created":"2023-08-08","cited_by_count":4,"area":null},{"id":"2403.08152","title":"Multi-Fidelity Reinforcement Learning for Time-Optimal Quadrotor Re-planning","created":"2024-03-13","cited_by_count":4,"area":"deeprl"},{"id":"2408.12130","title":"S-EPOA: Overcoming the Indistinguishability of Segments with Skill-Driven Preference-Based Reinforcement Learning","created":"2024-08-22","cited_by_count":4,"area":"deeprl"},{"id":"2506.05619","title":"Beyond RLHF and NLHF: Population-Proportional Alignment under an Axiomatic Framework","created":"2025-06-05","cited_by_count":4,"area":"alignment"},{"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":"2501.06946","title":"Learning Implicit Social Navigation Behavior using Deep Inverse Reinforcement Learning","created":"2025-01-12","cited_by_count":3,"area":"offlinerl"},{"id":"2506.00388","title":"CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries","created":"2025-05-31","cited_by_count":3,"area":"deeprl"},{"id":"2509.23802","title":"STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning","created":"2025-09-28","cited_by_count":3,"area":"alignment"},{"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":"2502.02921","title":"Robust Reward Alignment via Hypothesis Space Batch Cutting","created":"2025-02-05","cited_by_count":2,"area":"alignment"},{"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":"2406.03665","title":"Towards Dynamic Trend Filtering through Trend Point Detection with Reinforcement Learning","created":"2024-06-06","cited_by_count":1,"area":"deeprl"},{"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":"2408.16776","title":"Online Behavior Modification for Expressive User Control of RL-Trained Robots","created":"2024-08-15","cited_by_count":0,"area":"deeprl"},{"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":"2505.00382","title":"Approximation to Deep Q-Network by Stochastic Delay Differential Equations","created":"2025-05-01","cited_by_count":0,"area":"deeprl"},{"id":"2506.13741","title":"PB$^2$: Preference Space Exploration via Population-Based Methods in Preference-Based Reinforcement Learning","created":"2025-06-16","cited_by_count":0,"area":"deeprl"},{"id":"2512.08950","title":"Optimizing Algorithms for Mobile Health Interventions with Active Querying Optimization","created":"2025-11-27","cited_by_count":0,"area":"deeprl"},{"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},{"id":"2606.03963","title":"AgenticRL: Agentic Reinforcement Learning with Self-Refinement for Complex UAV Navigation","created":"2026-06-02","cited_by_count":0,"area":"agents"},{"id":"2607.11432","title":"On Generalizing Preference-based Reinforcement Learning to Multi-Objective Problems","created":"2026-07-13","cited_by_count":0,"area":"deeprl"},{"id":"2609.04066","title":"Subspace Inference Enables Efficient Active Reward Learning from Preferences","created":"2026-09-03","cited_by_count":0,"area":"alignment"}],"next_cursor":null}