{"total":97,"rows":[{"id":"2505.15134","title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","created":"2025-05-21","cited_by_count":166,"area":"lr"},{"id":"2309.11489","title":"Text2Reward: Reward Shaping with Language Models for Reinforcement Learning","created":"2023-09-20","cited_by_count":160,"area":"alignment"},{"id":"2203.13880","title":"Reinforcement Learning with Action-Free Pre-Training from Videos","created":"2022-03-25","cited_by_count":108,"area":null},{"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":"2303.00957","title":"Preference Transformer: Modeling Human Preferences using Transformers for RL","created":"2023-03-02","cited_by_count":79,"area":null},{"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":"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":"2402.17257","title":"RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences","created":"2024-02-27","cited_by_count":39,"area":"deeprl"},{"id":"2408.10215","title":"Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applications","created":"2024-07-22","cited_by_count":38,"area":"deeprl"},{"id":"2310.02054","title":"AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model","created":"2023-10-03","cited_by_count":37,"area":"diffusion"},{"id":"2301.12842","title":"Direct Preference-based Policy Optimization without Reward Modeling","created":"2023-01-30","cited_by_count":36,"area":"alignment"},{"id":"2305.16217","title":"Beyond Reward: Offline Preference-guided Policy Optimization","created":"2023-05-25","cited_by_count":35,"area":"alignment"},{"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":"2212.02779","title":"PrefRec: Recommender Systems with Human Preferences for Reinforcing Long-term User Engagement","created":"2022-12-06","cited_by_count":21,"area":null},{"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":"2507.04136","title":"A Technical Survey of Reinforcement Learning Techniques for Large Language Models","created":"2025-07-05","cited_by_count":21,"area":"lr"},{"id":"2406.02764","title":"Adaptive Preference Scaling for Reinforcement Learning with Human Feedback","created":"2024-06-04","cited_by_count":20,"area":"alignment"},{"id":"2406.15567","title":"SAIL: Self-Improving Efficient Online Alignment of Large Language Models","created":"2024-06-21","cited_by_count":20,"area":"alignment"},{"id":"2305.17400","title":"Query-Policy Misalignment in Preference-Based Reinforcement Learning","created":"2023-05-27","cited_by_count":15,"area":null},{"id":"2307.16348","title":"Rating-based Reinforcement Learning","created":"2023-07-30","cited_by_count":15,"area":null},{"id":"2310.03013","title":"SemiReward: A General Reward Model for Semi-supervised Learning","created":"2023-10-04","cited_by_count":14,"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":"2404.08828","title":"Hindsight PRIORs for Reward Learning from Human Preferences","created":"2024-04-12","cited_by_count":12,"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":"2402.17975","title":"Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards","created":"2024-02-28","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":"2503.13817","title":"VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized Preferences","created":"2025-03-18","cited_by_count":9,"area":"mllm"},{"id":"2210.09151","title":"Symbol Guided Hindsight Priors for Reward Learning from Human Preferences","created":"2022-10-17","cited_by_count":8,"area":"alignment"},{"id":"2408.11943","title":"Advances in Preference-based Reinforcement Learning: A Review","created":"2024-08-21","cited_by_count":8,"area":"deeprl"},{"id":"2409.06903","title":"Semi-Supervised Reward Modeling via Iterative Self-Training","created":"2024-09-10","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":"2410.17233","title":"ICPL: Few-shot In-context Preference Learning via LLMs","created":"2024-10-22","cited_by_count":7,"area":"alignment"},{"id":"2502.01616","title":"Preference VLM: Leveraging VLMs for Scalable Preference-Based Reinforcement Learning","created":"2025-02-03","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":"2507.14066","title":"Preference-based Multi-Objective Reinforcement Learning","created":"2025-07-18","cited_by_count":7,"area":"deeprl"},{"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":"2211.06527","title":"Rewards Encoding Environment Dynamics Improves Preference-based Reinforcement Learning","created":"2022-11-12","cited_by_count":4,"area":"alignment"},{"id":"2211.10861","title":"Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation","created":"2022-11-20","cited_by_count":4,"area":null},{"id":"2302.08738","title":"Exploiting Unlabeled Data for Feedback Efficient Human Preference based Reinforcement Learning","created":"2023-02-17","cited_by_count":4,"area":"alignment"},{"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":"2602.23876","title":"RF-Agent: Automated Reward Function Design via Language Agent Tree Search","created":"2026-02-27","cited_by_count":4,"area":"agents"},{"id":"2302.08733","title":"Data Driven Reward Initialization for Preference based Reinforcement Learning","created":"2023-02-17","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":"2410.01458","title":"From Reward Shaping to Q-Shaping: Achieving Unbiased Learning with LLM-Guided Knowledge","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2501.17431","title":"Human-Aligned Skill Discovery: Balancing Behaviour Exploration and Alignment","created":"2025-01-29","cited_by_count":3,"area":"alignment"},{"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":"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":"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":"2309.16935","title":"TranDRL: A Transformer-Driven Deep Reinforcement Learning Enabled Prescriptive Maintenance Framework","created":"2023-09-29","cited_by_count":2,"area":null},{"id":"2312.15160","title":"Human-AI Collaboration in Real-World Complex Environment with Reinforcement Learning","created":"2023-12-23","cited_by_count":2,"area":null},{"id":"2405.03341","title":"Enhancing Q-Learning with Large Language Model Heuristics","created":"2024-05-06","cited_by_count":2,"area":null},{"id":"2406.16293","title":"Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels","created":"2024-06-24","cited_by_count":2,"area":"deeprl"},{"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":"2502.02921","title":"Robust Reward Alignment via Hypothesis Space Batch Cutting","created":"2025-02-05","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":"2601.01904","title":"Evaluating Feature Dependent Noise in Preference-based Reinforcement Learning","created":"2026-01-05","cited_by_count":2,"area":"alignment"},{"id":"2307.05405","title":"Boosting Feedback Efficiency of Interactive Reinforcement Learning by Adaptive Learning from Scores","created":"2023-07-11","cited_by_count":1,"area":"alignment"},{"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":"2402.14244","title":"MENTOR: Guiding Hierarchical Reinforcement Learning with Human Feedback and Dynamic Distance Constraint","created":"2024-02-22","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":"2505.06357","title":"DAPPER: Discriminability-Aware Policy-to-Policy Preference-Based Reinforcement Learning for Query-Efficient Robot Skill Acquisition","created":"2025-05-09","cited_by_count":1,"area":"deeprl"},{"id":"2505.22092","title":"VIRAL: Vision-grounded Integration for Reward design And Learning","created":"2025-05-28","cited_by_count":1,"area":"alignment"},{"id":"2506.14648","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":"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":"2509.24467","title":"Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\\\"om Approximation","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2510.03545","title":"SketchPlan: Diffusion Based Drone Planning From Human Sketches","created":"2025-10-03","cited_by_count":1,"area":"diffusion"},{"id":"2510.13036","title":"Repairing Reward Functions with Feedback to Mitigate Reward Hacking","created":"2025-10-14","cited_by_count":1,"area":"alignment"},{"id":"2603.28053","title":"Reducing Oracle Feedback with Vision-Language Embeddings for Preference-Based RL","created":"2026-03-30","cited_by_count":1,"area":"deeprl"},{"id":"2606.00950","title":"COLLIE: Guiding Skill Discovery in Semantically Coherent Latent Space","created":"2026-05-31","cited_by_count":1,"area":null},{"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":"2606.23640","title":"Learning Process Rewards via Success Visitation Matching for Efficient RL","created":"2026-06-22","cited_by_count":1,"area":"deeprl"},{"id":"2606.31524","title":"On the Convergence of Self-Improving Online LLM Alignment","created":"2026-06-30","cited_by_count":1,"area":"alignment"},{"id":"2305.02882","title":"Simple Noisy Environment Augmentation for Reinforcement Learning","created":"2023-05-04","cited_by_count":0,"area":null},{"id":"2312.14436","title":"REBEL: Reward Regularization-Based Approach for Robotic Reinforcement Learning from Human Feedback","created":"2023-12-22","cited_by_count":0,"area":"alignment"},{"id":"2403.10160","title":"Online Policy Learning from Offline Preferences","created":"2024-03-15","cited_by_count":0,"area":null},{"id":"2406.06495","title":"Boosting Robustness in Preference-Based Reinforcement Learning with Dynamic Sparsity","created":"2024-06-10","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":"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":"2412.21001","title":"LEASE: Offline Preference-based Reinforcement Learning with High Sample Efficiency","created":"2024-12-30","cited_by_count":0,"area":"alignment"},{"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":"2509.14985","title":"PRISM: Product Retrieval In Shopping Carts using Hybrid Matching","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2510.15728","title":"RLAF: Reinforcement Learning from Automaton Feedback","created":"2025-10-17","cited_by_count":0,"area":"alignment"},{"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":"2601.09236","title":"Reward Learning through Ranking Mean Squared Error","created":"2026-01-14","cited_by_count":0,"area":"alignment"},{"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":"2604.24127","title":"Leveraging Human Feedback for Semantically-Relevant Skill Discovery","created":"2026-04-27","cited_by_count":0,"area":"alignment"},{"id":"2606.24622","title":"Themis: An explainable AI-enabled framework for Reinforcement Learning with Human Feedback","created":"2026-06-23","cited_by_count":0,"area":"alignment"},{"id":"2607.01721","title":"CoRe: Combined Rewards with Vision-Language Model Feedback for Preference-Aligned Reinforcement Learning","created":"2026-07-02","cited_by_count":0,"area":"mllm"},{"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":"2608.08604","title":"Multi-Agent Reinforcement Learning via Agent-Specific Preference","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2609.13982","title":"Rethinking the Implications of Human Feedback for Preference Learning in Human-Robot Collaboration","created":"2026-09-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}