{"total":60,"rows":[{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912,"area":"alignment"},{"id":"1811.06521","title":"Reward learning from human preferences and demonstrations in Atari","created":"2018-11-15","cited_by_count":316,"area":"alignment"},{"id":"2302.08215","title":"Aligning Language Models with Preferences through f-divergence Minimization","created":"2023-02-16","cited_by_count":120,"area":"alignment"},{"id":"2306.14111","title":"Is RLHF More Difficult than Standard RL?","created":"2023-06-25","cited_by_count":96,"area":"alignment"},{"id":"2402.00782","title":"Dense Reward for Free in Reinforcement Learning from Human Feedback","created":"2024-02-01","cited_by_count":78,"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":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58,"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":"2405.19107","title":"Offline Regularised Reinforcement Learning for Large Language Models Alignment","created":"2024-05-29","cited_by_count":48,"area":"alignment"},{"id":"2310.13595","title":"The History and Risks of Reinforcement Learning and Human Feedback","created":"2023-10-20","cited_by_count":42,"area":"alignment"},{"id":"1810.11748","title":"DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback","created":"2018-10-28","cited_by_count":41,"area":"alignment"},{"id":"2109.12750","title":"Learning Multimodal Rewards from Rankings","created":"2021-09-27","cited_by_count":41,"area":"alignment"},{"id":"2305.16217","title":"Beyond Reward: Offline Preference-guided Policy Optimization","created":"2023-05-25","cited_by_count":35,"area":"alignment"},{"id":"2406.01309","title":"REvolve: Reward Evolution with Large Language Models using Human Feedback","created":"2024-06-03","cited_by_count":23,"area":"alignment"},{"id":"2310.06147","title":"Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyond","created":"2023-10-09","cited_by_count":20,"area":"alignment"},{"id":"2312.00267","title":"Sample Efficient Preference Alignment in LLMs via Active Exploration","created":"2023-12-01","cited_by_count":18,"area":"alignment"},{"id":"2408.04190","title":"Listwise Reward Estimation for Offline Preference-based Reinforcement Learning","created":"2024-08-08","cited_by_count":14,"area":"alignment"},{"id":"2302.13507","title":"Active Reward Learning from Online Preferences","created":"2023-02-27","cited_by_count":13,"area":"alignment"},{"id":"2312.11819","title":"An Adaptive Placement and Parallelism Framework for Accelerating RLHF Training","created":"2023-12-19","cited_by_count":13,"area":"alignment"},{"id":"2505.10892","title":"Multi-Objective Preference Optimization: Improving Human Alignment of Generative Models","created":"2025-05-16","cited_by_count":13,"area":"alignment"},{"id":"2501.16727","title":"xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking","created":"2025-01-28","cited_by_count":11,"area":"alignment"},{"id":"2306.03615","title":"PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation","created":"2023-06-06","cited_by_count":9,"area":"alignment"},{"id":"2405.18688","title":"Efficient Preference-based Reinforcement Learning via Aligned Experience Estimation","created":"2024-05-29","cited_by_count":9,"area":"alignment"},{"id":"1709.03969","title":"Explore, Exploit or Listen: Combining Human Feedback and Policy Model to Speed up Deep Reinforcement Learning in 3D Worlds","created":"2017-09-12","cited_by_count":8,"area":"alignment"},{"id":"2101.08937","title":"Prior Preference Learning from Experts:Designing a Reward with Active Inference","created":"2021-01-22","cited_by_count":8,"area":"alignment"},{"id":"2509.15110","title":"TDRM: Smooth Reward Models with Temporal Difference for LLM RL and Inference","created":"2025-09-18","cited_by_count":8,"area":"alignment"},{"id":"2210.15906","title":"Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences","created":"2022-10-28","cited_by_count":7,"area":"alignment"},{"id":"2507.13158","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","created":"2025-07-17","cited_by_count":7,"area":"alignment"},{"id":"2210.02594","title":"Reward-Mixing MDPs with a Few Latent Contexts are Learnable","created":"2022-10-05","cited_by_count":5,"area":"alignment"},{"id":"2411.09341","title":"Approximated Variational Bayesian Inverse Reinforcement Learning for Large Language Model Alignment","created":"2024-11-14","cited_by_count":4,"area":"alignment"},{"id":"1809.08714","title":"Give me a hint! Navigating Image Databases using Human-in-the-loop Feedback","created":"2018-09-24","cited_by_count":3,"area":"alignment"},{"id":"2112.03482","title":"Combining Learning from Human Feedback and Knowledge Engineering to Solve Hierarchical Tasks in Minecraft","created":"2021-12-07","cited_by_count":3,"area":"alignment"},{"id":"2302.08733","title":"Data Driven Reward Initialization for Preference based Reinforcement Learning","created":"2023-02-17","cited_by_count":3,"area":"alignment"},{"id":"2404.13423","title":"PIPER: Primitive-Informed Preference-based Hierarchical Reinforcement Learning via Hindsight Relabeling","created":"2024-04-20","cited_by_count":3,"area":"alignment"},{"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":"2511.13765","title":"PROF: An LLM-based Reward Code Preference Optimization Framework for Offline Imitation Learning","created":"2025-11-14","cited_by_count":3,"area":"alignment"},{"id":"2209.14010","title":"Argumentative Reward Learning: Reasoning About Human Preferences","created":"2022-09-28","cited_by_count":2,"area":"alignment"},{"id":"2302.08734","title":"A State Augmentation based approach to Reinforcement Learning from Human Preferences","created":"2023-02-17","cited_by_count":2,"area":"alignment"},{"id":"2405.17618","title":"Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales","created":"2024-05-27","cited_by_count":2,"area":"alignment"},{"id":"2506.09183","title":"Multi-Task Reward Learning from Human Ratings","created":"2025-06-10","cited_by_count":2,"area":"alignment"},{"id":"2404.12150","title":"Aligning language models with human preferences","created":"2024-04-18","cited_by_count":1,"area":"alignment"},{"id":"2406.16258","title":"MEReQ: Max-Ent Residual-Q Inverse RL for Sample-Efficient Alignment from Intervention","created":"2024-06-24","cited_by_count":1,"area":"alignment"},{"id":"2407.13221","title":"Multimodal Label Relevance Ranking via Reinforcement Learning","created":"2024-07-18","cited_by_count":1,"area":"alignment"},{"id":"2409.20016","title":"Dynamic Policy Fusion for User Alignment Without Re-Interaction","created":"2024-09-30","cited_by_count":1,"area":"alignment"},{"id":"2501.15219","title":"Faster Machine Translation Ensembling with Reinforcement Learning and Competitive Correction","created":"2025-01-25","cited_by_count":1,"area":"alignment"},{"id":"2504.17282","title":"Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning","created":"2025-04-24","cited_by_count":1,"area":"alignment"},{"id":"2505.22092","title":"VIRAL: Vision-grounded Integration for Reward design And Learning","created":"2025-05-28","cited_by_count":1,"area":"alignment"},{"id":"2506.04464","title":"Leveraging Reward Models for Guiding Code Review Comment Generation","created":"2025-06-04","cited_by_count":1,"area":"alignment"},{"id":"2506.14648","title":"SENIOR: Efficient Query Selection and Preference-Guided Exploration in Preference-based Reinforcement Learning","created":"2025-06-17","cited_by_count":1,"area":"alignment"},{"id":"2602.07333","title":"High Fidelity Textual User Representation over Heterogeneous Sources via Reinforcement Learning","created":"2026-02-07","cited_by_count":1,"area":"alignment"},{"id":"2310.09358","title":"Bad Values but Good Behavior: Learning Highly Misspecified Bandits and MDPs","created":"2023-10-13","cited_by_count":0,"area":"alignment"},{"id":"2310.10556","title":"Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks","created":"2023-10-16","cited_by_count":0,"area":"alignment"},{"id":"2401.05710","title":"The Distributional Reward Critic Framework for Reinforcement Learning Under Perturbed Rewards","created":"2024-01-11","cited_by_count":0,"area":"alignment"},{"id":"2410.06118","title":"Optimizing the Training Schedule of Multilingual NMT using Reinforcement Learning","created":"2024-10-08","cited_by_count":0,"area":"alignment"},{"id":"2411.00252","title":"IO Transformer: Evaluating SwinV2-Based Reward Models for Computer Vision","created":"2024-10-31","cited_by_count":0,"area":"alignment"},{"id":"2504.14732","title":"Reinforcement Learning from Multi-level and Episodic Human Feedback","created":"2025-04-20","cited_by_count":0,"area":"alignment"},{"id":"2507.19725","title":"Minding Motivation: The Effect of Intrinsic Motivation on Agent Behaviors","created":"2025-07-26","cited_by_count":0,"area":"alignment"},{"id":"2607.07693","title":"Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF","created":"2026-07-08","cited_by_count":0,"area":"alignment"},{"id":"2607.29559","title":"LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback","created":"2026-07-31","cited_by_count":0,"area":"alignment"},{"id":"2608.02951","title":"SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling","created":"2026-08-03","cited_by_count":0,"area":"alignment"}],"next_cursor":null}