{"total":63,"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":"2310.12921","title":"Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning","created":"2023-10-19","cited_by_count":165,"area":"mllm"},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2205.12401","title":"Reward Uncertainty for Exploration in Preference-based Reinforcement Learning","created":"2022-05-24","cited_by_count":61,"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":"2403.03185","title":"Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking","created":"2024-03-05","cited_by_count":50,"area":"alignment"},{"id":"2302.08560","title":"Dual RL: Unification and New Methods for Reinforcement and Imitation Learning","created":"2023-02-16","cited_by_count":48,"area":"offlinerl"},{"id":"2310.09144","title":"Goodhart's Law in Reinforcement Learning","created":"2023-10-13","cited_by_count":41,"area":null},{"id":"2410.05584","title":"Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?","created":"2024-10-08","cited_by_count":31,"area":"lr"},{"id":"2212.03201","title":"Misspecification in Inverse Reinforcement Learning","created":"2022-12-06","cited_by_count":27,"area":"offlinerl"},{"id":"2212.04717","title":"On the Sensitivity of Reward Inference to Misspecified Human Models","created":"2022-12-09","cited_by_count":25,"area":null},{"id":"2506.15421","title":"Reward Models in Deep Reinforcement Learning: A Survey","created":"2025-06-18","cited_by_count":25,"area":"alignment"},{"id":"2301.03652","title":"On The Fragility of Learned Reward Functions","created":"2023-01-09","cited_by_count":21,"area":"alignment"},{"id":"2201.10081","title":"Dynamics-Aware Comparison of Learned Reward Functions","created":"2022-01-25","cited_by_count":17,"area":null},{"id":"2209.10974","title":"Identifiability and generalizability from multiple experts in Inverse Reinforcement Learning","created":"2022-09-22","cited_by_count":16,"area":"offlinerl"},{"id":"2309.15257","title":"STARC: A General Framework For Quantifying Differences Between Reward Functions","created":"2023-09-26","cited_by_count":15,"area":null},{"id":"2504.20168","title":"MICE for CATs: Model-Internal Confidence Estimation for Calibrating Agents with Tools","created":"2025-04-28","cited_by_count":15,"area":"agents"},{"id":"2203.11409","title":"A Primer on Maximum Causal Entropy Inverse Reinforcement Learning","created":"2022-03-22","cited_by_count":13,"area":"offlinerl"},{"id":"2210.11846","title":"Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunities","created":"2022-10-21","cited_by_count":13,"area":null},{"id":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","cited_by_count":11,"area":"offlinerl"},{"id":"2106.10394","title":"Uncertain Decisions Facilitate Better Preference Learning","created":"2021-06-19","cited_by_count":10,"area":"offlinerl"},{"id":"2310.18591","title":"Inverse Decision Modeling: Learning Interpretable Representations of Behavior","created":"2023-10-28","cited_by_count":10,"area":null},{"id":"2502.20630","title":"Subtask-Aware Visual Reward Learning from Segmented Demonstrations","created":"2025-02-28","cited_by_count":10,"area":"deeprl"},{"id":"2503.05996","title":"Towards Improving Reward Design in RL: A Reward Alignment Metric for RL Practitioners","created":"2025-03-08","cited_by_count":10,"area":null},{"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":"2308.02435","title":"Designing Fiduciary Artificial Intelligence","created":"2023-07-27","cited_by_count":8,"area":null},{"id":"2203.13553","title":"Preprocessing Reward Functions for Interpretability","created":"2022-03-25","cited_by_count":7,"area":"alignment"},{"id":"2103.04706","title":"A Taxonomy of Similarity Metrics for Markov Decision Processes","created":"2021-03-08","cited_by_count":6,"area":null},{"id":"2406.15753","title":"The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret","created":"2024-06-22","cited_by_count":6,"area":"alignment"},{"id":"2208.09570","title":"Calculus on MDPs: Potential Shaping as a Gradient","created":"2022-08-20","cited_by_count":4,"area":null},{"id":"2210.07426","title":"Skill-Based Reinforcement Learning with Intrinsic Reward Matching","created":"2022-10-14","cited_by_count":4,"area":null},{"id":"2310.08164","title":"Interpreting Learned Feedback Patterns in Large Language Models","created":"2023-10-12","cited_by_count":4,"area":"alignment"},{"id":"2312.03881","title":"FoMo Rewards: Can we cast foundation models as reward functions?","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2403.06854","title":"Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification","created":"2024-03-11","cited_by_count":4,"area":"offlinerl"},{"id":"2103.02863","title":"Inverse Reinforcement Learning with Explicit Policy Estimates","created":"2021-03-04","cited_by_count":3,"area":"offlinerl"},{"id":"2402.14569","title":"Transformable Gaussian Reward Function for Socially-Aware Navigation with Deep Reinforcement Learning","created":"2024-02-22","cited_by_count":3,"area":"deeprl"},{"id":"2501.00989","title":"Bootstrapped Reward Shaping","created":"2025-01-02","cited_by_count":3,"area":"deeprl"},{"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":"2510.18913","title":"ADPO: Anchored Direct Preference Optimization","created":"2025-10-21","cited_by_count":3,"area":"alignment"},{"id":"2106.01777","title":"LiMIIRL: Lightweight Multiple-Intent Inverse Reinforcement Learning","created":"2021-06-03","cited_by_count":2,"area":"offlinerl"},{"id":"2210.01007","title":"Reward Learning with Trees: Methods and Evaluation","created":"2022-10-03","cited_by_count":2,"area":"alignment"},{"id":"2402.15821","title":"Cooperation and Control in Delegation Games","created":"2024-02-24","cited_by_count":2,"area":null},{"id":"2404.17687","title":"Knowledge Transfer for Cross-Domain Reinforcement Learning: A Systematic Review","created":"2024-04-26","cited_by_count":2,"area":"deeprl"},{"id":"2505.06273","title":"Policy-labeled Preference Learning: Is Preference Enough for RLHF?","created":"2025-05-06","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":"2403.06003","title":"A Generalized Acquisition Function for Preference-based Reward Learning","created":"2024-03-09","cited_by_count":1,"area":null},{"id":"2407.09809","title":"Preserving the Privacy of Reward Functions in MDPs through Deception","created":"2024-07-13","cited_by_count":1,"area":null},{"id":"2408.12110","title":"Pareto Inverse Reinforcement Learning for Diverse Expert Policy Generation","created":"2024-08-22","cited_by_count":1,"area":"offlinerl"},{"id":"2502.20957","title":"Reward Dimension Reduction for Scalable Multi-Objective Reinforcement Learning","created":"2025-02-28","cited_by_count":1,"area":"deeprl"},{"id":"2605.20609","title":"Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement Learning","created":"2026-05-20","cited_by_count":1,"area":"offlinerl"},{"id":"2305.16924","title":"Learning Interpretable Models of Aircraft Handling Behaviour by Reinforcement Learning from Human Feedback","created":"2023-05-26","cited_by_count":0,"area":"alignment"},{"id":"2306.13004","title":"Can Differentiable Decision Trees Enable Interpretable Reward Learning from Human Feedback?","created":"2023-06-22","cited_by_count":0,"area":"alignment"},{"id":"2407.08324","title":"A Cantor-Kantorovich Metric Between Markov Decision Processes with Application to Transfer Learning","created":"2024-07-11","cited_by_count":0,"area":null},{"id":"2505.16833","title":"Strategically Linked Decisions in Long-Term Planning and Reinforcement Learning","created":"2025-05-22","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":"2602.15206","title":"MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2603.12324","title":"Thermodynamics of Reinforcement Learning Curricula","created":"2026-03-12","cited_by_count":0,"area":"deeprl"},{"id":"2605.09217","title":"Learning the Preferences of a Learning Agent","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.09124","title":"A Regret Minimization Framework on Preference Learning in Large Language Models","created":"2026-06-08","cited_by_count":0,"area":"alignment"},{"id":"2607.19281","title":"A Reinforcement-Learning-Augmented Liquid-Fueled Reactor Network Model for Predicting Lean Blowout in Gas Turbine Combustors","created":"2026-07-21","cited_by_count":0,"area":"deeprl"},{"id":"2608.03875","title":"Enhancing VLM Reward Models Through Structure-Aware Fine-Tuning","created":"2026-08-04","cited_by_count":0,"area":"alignment"},{"id":"2609.34126","title":"JET: Judge-Guided Evolution at Test Time for Agent Programs","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.04364","title":"A Bird's-Eye View of Iterative Reward Design","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}