{"total":87,"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":"2408.10075","title":"Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning","created":"2024-08-19","cited_by_count":155,"area":"alignment"},{"id":"2402.18571","title":"Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards","created":"2024-02-28","cited_by_count":148,"area":"alignment"},{"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":"2005.02575","title":"Active Preference-Based Gaussian Process Regression for Reward Learning","created":"2020-05-06","cited_by_count":71,"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":"2301.02555","title":"\"No, to the Right\" -- Online Language Corrections for Robotic Manipulation via Shared Autonomy","created":"2023-01-06","cited_by_count":60,"area":null},{"id":"2301.01392","title":"Benchmarks and Algorithms for Offline Preference-Based Reward Learning","created":"2023-01-03","cited_by_count":56,"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":"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":"2109.12750","title":"Learning Multimodal Rewards from Rankings","created":"2021-09-27","cited_by_count":41,"area":"alignment"},{"id":"2312.06853","title":"LLF-Bench: Benchmark for Interactive Learning from Language Feedback","created":"2023-12-11","cited_by_count":33,"area":null},{"id":"2503.08663","title":"Generating Robot Constitutions & Benchmarks for Semantic Safety","created":"2025-03-11","cited_by_count":33,"area":null},{"id":"2312.09337","title":"Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences","created":"2023-12-14","cited_by_count":26,"area":"alignment"},{"id":"2301.11774","title":"Reinforcement Learning from Diverse Human Preferences","created":"2023-01-27","cited_by_count":24,"area":"alignment"},{"id":"2311.14115","title":"A density estimation perspective on learning from pairwise human preferences","created":"2023-11-23","cited_by_count":23,"area":"alignment"},{"id":"2507.01915","title":"Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models","created":"2025-07-02","cited_by_count":23,"area":"alignment"},{"id":"2210.10765","title":"When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning","created":"2022-10-19","cited_by_count":21,"area":null},{"id":"2107.09251","title":"Offline Preference-Based Apprenticeship Learning","created":"2021-07-20","cited_by_count":17,"area":"offlinerl"},{"id":"2402.07157","title":"Natural Language Reinforcement Learning","created":"2024-02-11","cited_by_count":17,"area":"lr"},{"id":"2305.17400","title":"Query-Policy Misalignment in Preference-Based Reinforcement Learning","created":"2023-05-27","cited_by_count":15,"area":null},{"id":"2501.08259","title":"FDPP: Fine-tune Diffusion Policy with Human Preference","created":"2025-01-14","cited_by_count":15,"area":"diffusion"},{"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":"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":"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":"2303.00894","title":"Active Reward Learning from Multiple Teachers","created":"2023-03-02","cited_by_count":13,"area":"alignment"},{"id":"2307.11049","title":"Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback","created":"2023-07-20","cited_by_count":13,"area":"alignment"},{"id":"2310.20608","title":"Autonomous Robotic Reinforcement Learning with Asynchronous Human Feedback","created":"2023-10-31","cited_by_count":13,"area":null},{"id":"2107.13507","title":"The Reasonable Crowd: Towards evidence-based and interpretable models of driving behavior","created":"2021-07-28","cited_by_count":12,"area":null},{"id":"2106.10394","title":"Uncertain Decisions Facilitate Better Preference Learning","created":"2021-06-19","cited_by_count":10,"area":"offlinerl"},{"id":"2405.11647","title":"Hummer: Towards Limited Competitive Preference Dataset","created":"2024-05-19","cited_by_count":10,"area":"alignment"},{"id":"2505.19241","title":"ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment","created":"2025-05-25","cited_by_count":10,"area":"lr"},{"id":"2103.02727","title":"Preference-based Learning of Reward Function Features","created":"2021-03-03","cited_by_count":9,"area":"alignment"},{"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":"2303.04912","title":"Embodied Active Learning of Relational State Abstractions for Bilevel Planning","created":"2023-03-08","cited_by_count":8,"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":"2406.15599","title":"Pareto-Optimal Learning from Preferences with Hidden Context","created":"2024-06-21","cited_by_count":8,"area":"alignment"},{"id":"2302.03805","title":"Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative Feedback","created":"2023-02-07","cited_by_count":7,"area":null},{"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":"2103.04289","title":"Learning Human Rewards by Inferring Their Latent Intelligence Levels in Multi-Agent Games: A Theory-of-Mind Approach with Application to Driving Data","created":"2021-03-07","cited_by_count":6,"area":"driving"},{"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":"2405.03803","title":"MoDiPO: text-to-motion alignment via AI-feedback-driven Direct Preference Optimization","created":"2024-05-06","cited_by_count":6,"area":"diffusion"},{"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":"2511.02966","title":"Inference-Time Personalized Alignment with a Few User Preference Queries","created":"2025-11-04","cited_by_count":6,"area":null},{"id":"2111.09884","title":"Assisted Robust Reward Design","created":"2021-11-18","cited_by_count":5,"area":null},{"id":"2411.14251","title":"Natural Language Reinforcement Learning","created":"2024-11-21","cited_by_count":5,"area":"lr"},{"id":"2211.06527","title":"Rewards Encoding Environment Dynamics Improves Preference-based Reinforcement Learning","created":"2022-11-12","cited_by_count":4,"area":"alignment"},{"id":"2410.13957","title":"Goal Inference from Open-Ended Dialog","created":"2024-10-17","cited_by_count":4,"area":null},{"id":"2307.10434","title":"Learning Formal Specifications from Membership and Preference Queries","created":"2023-07-19","cited_by_count":3,"area":null},{"id":"2406.18450","title":"Preference Elicitation for Offline Reinforcement Learning","created":"2024-06-26","cited_by_count":3,"area":"offlinerl"},{"id":"2604.17501","title":"CoAct: Co-Active LLM Preference Learning with Human-AI Synergy","created":"2026-04-19","cited_by_count":3,"area":"alignment"},{"id":"2409.02337","title":"Coaching a Robotic Sonographer: Learning Robotic Ultrasound with Sparse Expert's Feedback","created":"2024-09-03","cited_by_count":2,"area":null},{"id":"2411.06568","title":"Meta-Learning Objectives for Preference Optimization","created":"2024-11-10","cited_by_count":2,"area":"alignment"},{"id":"2506.12248","title":"ProVox: Personalization and Proactive Planning for Situated Human-Robot Collaboration","created":"2025-06-13","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":"2510.06038","title":"From Learning to Mastery: Achieving Safe and Efficient Real-World Autonomous Driving with Human-In-The-Loop Reinforcement Learning","created":"2025-10-07","cited_by_count":2,"area":"driving"},{"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":"2308.08017","title":"Active Inverse Learning in Stackelberg Trajectory Games","created":"2023-08-15","cited_by_count":1,"area":null},{"id":"2311.02099","title":"A Safe Preference Learning Approach for Personalization with Applications to Autonomous Vehicles","created":"2023-10-30","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":"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":"2507.00611","title":"Residual Reward Models: Leveraging Prior Knowledge for Efficient Preference-based Reinforcement Learning in Robotics","created":"2025-07-01","cited_by_count":1,"area":"alignment"},{"id":"2508.15119","title":"Flexible Agent Alignment with Goal Inference from Open-Ended Dialog","created":"2025-08-20","cited_by_count":1,"area":"agents"},{"id":"2604.26360","title":"Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking","created":"2026-04-29","cited_by_count":1,"area":"alignment"},{"id":"2606.32027","title":"Freeform Preference Learning for Robotic Manipulation","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2608.28620","title":"Preference Elicitation for Policy Optimization and Application to Aligning Heart Transplantation with Human Values","created":"2026-07-29","cited_by_count":1,"area":"alignment"},{"id":"2402.15826","title":"Reward Design for Justifiable Sequential Decision-Making","created":"2024-02-24","cited_by_count":0,"area":"alignment"},{"id":"2408.05610","title":"Representation Alignment from Human Feedback for Cross-Embodiment Reward Learning from Mixed-Quality Demonstrations","created":"2024-08-10","cited_by_count":0,"area":"alignment"},{"id":"2506.03568","title":"Confidence-Guided Human-AI Collaboration: Reinforcement Learning with Distributional Proxy Value Propagation for Autonomous Driving","created":"2025-06-04","cited_by_count":0,"area":"driving"},{"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":"2601.16906","title":"The Trajectory Alignment Coefficient in Two Acts: From Reward Tuning to Reward Learning","created":"2026-01-23","cited_by_count":0,"area":"alignment"},{"id":"2601.18751","title":"Trust, Don't Trust, or Flip: Robust Preference-Based Reinforcement Learning with Multi-Expert Feedback","created":"2026-01-26","cited_by_count":0,"area":"alignment"},{"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":"2604.01312","title":"Preference learning in shades of gray: Interpretable and bias-aware reward modeling for human preferences","created":"2026-04-01","cited_by_count":0,"area":"alignment"},{"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":"2607.13172","title":"Learning Safe Agent Behaviour from Human Preferences and Justifications via World Models","created":"2026-07-14","cited_by_count":0,"area":"wm"},{"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":"2609.09685","title":"ALIGN-HOLD: Experience Alignment for Real-Time Hold Control in Large-Scale Ride-Hailing Matching at DiDi","created":"2026-09-09","cited_by_count":0,"area":"alignment"},{"id":"2609.38938","title":"Robust Risk-Sensitive Reinforcement Learning from Corrupted Human Feedback","created":"2026-09-30","cited_by_count":0,"area":"alignment"},{"id":"2609.39055","title":"The Missing Coefficients: Bayesian Pairwise Merging for Model Personalization","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.40165","title":"PrefPI: Preference-Guided Steering into Out-of-Distribution Behaviors","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}