{"total":79,"rows":[{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656,"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":"2305.13122","title":"Policy Representation via Diffusion Probability Model for Reinforcement Learning","created":"2023-05-22","cited_by_count":112,"area":"diffusion"},{"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":"2402.08265","title":"A Dense Reward View on Aligning Text-to-Image Diffusion with Preference","created":"2024-02-13","cited_by_count":55,"area":"diffusion"},{"id":"2402.17257","title":"RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences","created":"2024-02-27","cited_by_count":39,"area":"deeprl"},{"id":"2505.20065","title":"SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety","created":"2025-05-26","cited_by_count":37,"area":"alignment"},{"id":"2305.16217","title":"Beyond Reward: Offline Preference-guided Policy Optimization","created":"2023-05-25","cited_by_count":35,"area":"alignment"},{"id":"2306.00398","title":"Preference-grounded Token-level Guidance for Language Model Fine-tuning","created":"2023-06-01","cited_by_count":31,"area":"alignment"},{"id":"2506.15421","title":"Reward Models in Deep Reinforcement Learning: A Survey","created":"2025-06-18","cited_by_count":25,"area":"alignment"},{"id":"2402.02423","title":"Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback","created":"2024-02-04","cited_by_count":21,"area":"alignment"},{"id":"2407.07787","title":"Continuous Control with Coarse-to-fine Reinforcement Learning","created":"2024-07-10","cited_by_count":17,"area":"deeprl"},{"id":"2310.14196","title":"Learning to Discern: Imitating Heterogeneous Human Demonstrations with Preference and Representation Learning","created":"2023-10-22","cited_by_count":15,"area":"offlinerl"},{"id":"2408.04190","title":"Listwise Reward Estimation for Offline Preference-based Reinforcement Learning","created":"2024-08-08","cited_by_count":14,"area":"alignment"},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2404.08828","title":"Hindsight PRIORs for Reward Learning from Human Preferences","created":"2024-04-12","cited_by_count":12,"area":"alignment"},{"id":"2501.02790","title":"Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model","created":"2025-01-06","cited_by_count":12,"area":"alignment"},{"id":"2405.19806","title":"Preference Alignment with Flow Matching","created":"2024-05-30","cited_by_count":11,"area":"alignment"},{"id":"2309.10790","title":"Guide Your Agent with Adaptive Multimodal Rewards","created":"2023-09-19","cited_by_count":10,"area":"offlinerl"},{"id":"2409.05622","title":"Forward KL Regularized Preference Optimization for Aligning Diffusion Policies","created":"2024-09-09","cited_by_count":10,"area":"diffusion"},{"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":"2404.04920","title":"Regularized Conditional Diffusion Model for Multi-Task Preference Alignment","created":"2024-04-07","cited_by_count":9,"area":"diffusion"},{"id":"2405.18688","title":"Efficient Preference-based Reinforcement Learning via Aligned Experience Estimation","created":"2024-05-29","cited_by_count":9,"area":"alignment"},{"id":"2312.11442","title":"Explore 3D Dance Generation via Reward Model from Automatically-Ranked Demonstrations","created":"2023-12-18","cited_by_count":8,"area":null},{"id":"2603.18683","title":"HISR: Hindsight Information Modulated Segmental Process Rewards For Multi-turn Agentic Reinforcement Learning","created":"2026-03-19","cited_by_count":8,"area":"agents"},{"id":"2502.00634","title":"SimulPL: Aligning Human Preferences in Simultaneous Machine Translation","created":"2025-02-02","cited_by_count":7,"area":"alignment"},{"id":"2504.19342","title":"Contextual Online Uncertainty-Aware Preference Learning for Human Feedback","created":"2025-04-27","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":"2503.03796","title":"Human Implicit Preference-Based Policy Fine-tuning for Multi-Agent Reinforcement Learning in USV Swarm","created":"2025-03-05","cited_by_count":6,"area":"agents"},{"id":"2503.04793","title":"Sentence-level Reward Model can Generalize Better for Aligning LLM from Human Preference","created":"2025-03-01","cited_by_count":5,"area":"alignment"},{"id":"2402.15957","title":"DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning","created":"2024-02-25","cited_by_count":4,"area":"deeprl"},{"id":"2407.03964","title":"Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models","created":"2024-07-04","cited_by_count":4,"area":null},{"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":"2410.07525","title":"Offline Inverse Constrained Reinforcement Learning for Safe-Critical Decision Making in Healthcare","created":"2024-10-10","cited_by_count":4,"area":null},{"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":"2501.06416","title":"Influencing Humans to Conform to Preference Models for RLHF","created":"2025-01-11","cited_by_count":4,"area":"alignment"},{"id":"2502.00281","title":"Sigmoid Self-Attention has Lower Sample Complexity than Softmax Self-Attention: A Mixture-of-Experts Perspective","created":"2025-02-01","cited_by_count":4,"area":"moe"},{"id":"2507.23391","title":"Policy Learning from Large Vision-Language Model Feedback without Reward Modeling","created":"2025-07-31","cited_by_count":4,"area":"mllm"},{"id":"2311.01990","title":"Conditions on Preference Relations that Guarantee the Existence of Optimal Policies","created":"2023-11-03","cited_by_count":3,"area":"alignment"},{"id":"2406.01931","title":"Dishonesty in Helpful and Harmless Alignment","created":"2024-06-04","cited_by_count":3,"area":"alignment"},{"id":"2406.18450","title":"Preference Elicitation for Offline Reinforcement Learning","created":"2024-06-26","cited_by_count":3,"area":"offlinerl"},{"id":"2407.04451","title":"Hindsight Preference Learning for Offline Preference-based Reinforcement Learning","created":"2024-07-05","cited_by_count":3,"area":null},{"id":"2504.10002","title":"FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functions","created":"2025-04-14","cited_by_count":3,"area":"alignment"},{"id":"2505.18595","title":"MisoDICE: Multi-Agent Imitation from Unlabeled Mixed-Quality Demonstrations","created":"2025-05-24","cited_by_count":3,"area":"agents"},{"id":"2506.00388","title":"CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries","created":"2025-05-31","cited_by_count":3,"area":"deeprl"},{"id":"2507.13171","title":"Aligning Humans and Robots via Reinforcement Learning from Implicit Human Feedback","created":"2025-07-17","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":"2409.07268","title":"Multi-Type Preference Learning: Empowering Preference-Based Reinforcement Learning with Equal Preferences","created":"2024-09-11","cited_by_count":2,"area":"deeprl"},{"id":"2410.11330","title":"Evolutionary Retrofitting","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2410.20176","title":"Beyond Simple Sum of Delayed Rewards: Non-Markovian Reward Modeling for Reinforcement Learning","created":"2024-10-26","cited_by_count":2,"area":"alignment"},{"id":"2503.05306","title":"Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning","created":"2025-03-07","cited_by_count":2,"area":null},{"id":"2504.15472","title":"LAPP: Large Language Model Feedback for Preference-Driven Reinforcement Learning","created":"2025-04-21","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":"2509.21828","title":"Preference-Guided Learning for Sparse-Reward Multi-Agent Reinforcement Learning","created":"2025-09-26","cited_by_count":2,"area":"agents"},{"id":"2406.10445","title":"Binary Reward Labeling: Bridging Offline Preference and Reward-Based Reinforcement Learning","created":"2024-06-14","cited_by_count":1,"area":"alignment"},{"id":"2409.19949","title":"Task-Agnostic Pre-training and Task-Guided Fine-tuning for Versatile Diffusion Planner","created":"2024-09-30","cited_by_count":1,"area":"diffusion"},{"id":"2503.00930","title":"Behavior Preference Regression for Offline Reinforcement Learning","created":"2025-03-02","cited_by_count":1,"area":"alignment"},{"id":"2503.18347","title":"Latent Embedding Adaptation for Human Preference Alignment in Diffusion Planners","created":"2025-03-24","cited_by_count":1,"area":"alignment"},{"id":"2605.00384","title":"PrefMoE: Robust Preference Modeling with Mixture-of-Experts Reward Learning","created":"2026-05-01","cited_by_count":1,"area":"deeprl"},{"id":"2606.01123","title":"From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning","created":"2026-05-31","cited_by_count":1,"area":"alignment"},{"id":"2401.00330","title":"Two-Step Offline Preference-Based Reinforcement Learning with Constrained Actions","created":"2023-12-30","cited_by_count":0,"area":null},{"id":"2402.03771","title":"Reinforcement Learning from Bagged Reward","created":"2024-02-06","cited_by_count":0,"area":"deeprl"},{"id":"2407.06503","title":"Preference-Guided Reinforcement Learning for Efficient Exploration","created":"2024-07-09","cited_by_count":0,"area":"deeprl"},{"id":"2410.08307","title":"UNIQ: Offline Inverse Q-learning for Avoiding Undesirable Demonstrations","created":"2024-10-10","cited_by_count":0,"area":"offlinerl"},{"id":"2412.21001","title":"LEASE: Offline Preference-based Reinforcement Learning with High Sample Efficiency","created":"2024-12-30","cited_by_count":0,"area":"alignment"},{"id":"2504.12557","title":"TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels","created":"2025-04-17","cited_by_count":0,"area":"deeprl"},{"id":"2505.21182","title":"Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations","created":"2025-05-27","cited_by_count":0,"area":"offlinerl"},{"id":"2508.18817","title":"Learning Acrobatic Flight from Preferences","created":"2025-08-26","cited_by_count":0,"area":"deeprl"},{"id":"2510.07624","title":"From Data to Rewards: a Bilevel Optimization Perspective on Maximum Likelihood Estimation","created":"2025-10-08","cited_by_count":0,"area":"deeprl"},{"id":"2512.00050","title":"Reinforcement Learning from Implicit Neural Feedback for Human-Aligned Robot Control","created":"2025-11-18","cited_by_count":0,"area":"alignment"},{"id":"2512.14138","title":"LAPPI: Interactive Optimization with LLM-Assisted Preference-Based Problem Instantiation","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2602.20643","title":"TrajGPT-R: Generating Urban Mobility Trajectory with Reinforcement Learning-Enhanced Generative Pre-trained Transformer","created":"2026-02-24","cited_by_count":0,"area":"offlinerl"},{"id":"2604.02349","title":"OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2606.11982","title":"PAWS: Preference Learning with Advantage-Weighted Segments","created":"2026-06-10","cited_by_count":0,"area":"deeprl"},{"id":"2607.01925","title":"SPLC: Social Preference Learning for Crowd Robot Navigation","created":"2026-07-02","cited_by_count":0,"area":"offlinerl"},{"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":"2608.02951","title":"SP3O: Reinforcement Learning from Segment Preferences without Reward Modeling","created":"2026-08-03","cited_by_count":0,"area":"alignment"},{"id":"2609.32827","title":"Improving LLM Collaboration via Multi-Agent Preference Learning","created":"2026-09-26","cited_by_count":0,"area":"agents"}],"next_cursor":null}