{"total":33,"rows":[{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2407.08639","title":"$\\beta$-DPO: Direct Preference Optimization with Dynamic $\\beta$","created":"2024-07-11","cited_by_count":90,"area":"alignment"},{"id":"2410.18252","title":"Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models","created":"2024-10-23","cited_by_count":70,"area":"alignment"},{"id":"1902.04257","title":"Deep Reinforcement Learning from Policy-Dependent Human Feedback","created":"2019-02-12","cited_by_count":56,"area":"alignment"},{"id":"2308.02585","title":"PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback","created":"2023-08-03","cited_by_count":40,"area":"alignment"},{"id":"1911.00459","title":"Positive-Unlabeled Reward Learning","created":"2019-11-01","cited_by_count":37,"area":"alignment"},{"id":"2108.05382","title":"Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedback","created":"2021-08-11","cited_by_count":35,"area":"alignment"},{"id":"2410.04612","title":"Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF","created":"2024-10-06","cited_by_count":30,"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":"2406.12168","title":"BPO: Staying Close to the Behavior LLM Creates Better Online LLM Alignment","created":"2024-06-18","cited_by_count":9,"area":"alignment"},{"id":"2405.20830","title":"Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment","created":"2024-05-31","cited_by_count":7,"area":"alignment"},{"id":"2211.05750","title":"Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control","created":"2022-11-10","cited_by_count":6,"area":"alignment"},{"id":"2505.19731","title":"Proximal Point Nash Learning from Human Feedback","created":"2025-05-26","cited_by_count":5,"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":"2305.07036","title":"GFlowNets with Human Feedback","created":"2023-05-11","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":"2501.17431","title":"Human-Aligned Skill Discovery: Balancing Behaviour Exploration and Alignment","created":"2025-01-29","cited_by_count":3,"area":"alignment"},{"id":"2506.03519","title":"An Efficient Task-Oriented Dialogue Policy: Evolutionary Reinforcement Learning Injected by Elite Individuals","created":"2025-06-04","cited_by_count":2,"area":"alignment"},{"id":"2506.12529","title":"Similarity as Reward Alignment: Robust and Versatile Preference-based Reinforcement Learning","created":"2025-06-14","cited_by_count":2,"area":"alignment"},{"id":"2508.17000","title":"KL-Regularised Q-Learning: A Token-level Action-Value perspective on Online RLHF","created":"2025-08-23","cited_by_count":2,"area":"alignment"},{"id":"2603.09400","title":"Reward Prediction with Factorized World States","created":"2026-03-10","cited_by_count":2,"area":"alignment"},{"id":"2302.11917","title":"Diverse Policy Optimization for Structured Action Space","created":"2023-02-23","cited_by_count":1,"area":"alignment"},{"id":"2403.19024","title":"Exploiting Symmetry in Dynamics for Model-Based Reinforcement Learning with Asymmetric Rewards","created":"2024-03-27","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":"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":"2508.07126","title":"Pref-GUIDE: Continual Policy Learning from Real-Time Human Feedback via Preference-Based Learning","created":"2025-08-10","cited_by_count":1,"area":"alignment"},{"id":"2603.05066","title":"Reward-Conditioned Reinforcement Learning","created":"2026-03-05","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":"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":"2502.17538","title":"Policy Learning with a Natural Language Action Space: A Causal Approach","created":"2025-02-24","cited_by_count":0,"area":"alignment"},{"id":"2510.15728","title":"RLAF: Reinforcement Learning from Automaton Feedback","created":"2025-10-17","cited_by_count":0,"area":"alignment"},{"id":"2604.24127","title":"Leveraging Human Feedback for Semantically-Relevant Skill Discovery","created":"2026-04-27","cited_by_count":0,"area":"alignment"},{"id":"2606.26787","title":"AIGP: An LLM-Based Framework for Long-Term Value Alignment in E-Commerce Pricing","created":"2026-06-25","cited_by_count":0,"area":"alignment"}],"next_cursor":null}