{"total":260,"rows":[{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055,"area":"alignment"},{"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":"2306.16927","title":"End-to-end Autonomous Driving: Challenges and Frontiers","created":"2023-06-29","cited_by_count":490,"area":"driving"},{"id":"2310.17596","title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","created":"2023-10-26","cited_by_count":327,"area":"offlinerl"},{"id":"2310.03716","title":"A Long Way to Go: Investigating Length Correlations in RLHF","created":"2023-10-05","cited_by_count":291,"area":"alignment"},{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253,"area":null},{"id":"2301.11270","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","created":"2023-01-26","cited_by_count":247,"area":"alignment"},{"id":"2309.02473","title":"A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges","created":"2023-09-05","cited_by_count":148,"area":"offlinerl"},{"id":"2402.18571","title":"Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards","created":"2024-02-28","cited_by_count":148,"area":"alignment"},{"id":"2303.07280","title":"Vision-Language Models as Success Detectors","created":"2023-03-13","cited_by_count":142,"area":"mllm"},{"id":"2310.07899","title":"RoboCLIP: One Demonstration is Enough to Learn Robot Policies","created":"2023-10-11","cited_by_count":134,"area":"offlinerl"},{"id":"2006.04678","title":"Primal Wasserstein Imitation Learning","created":"2020-06-08","cited_by_count":121,"area":"offlinerl"},{"id":"2211.08416","title":"Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment","created":"2022-11-15","cited_by_count":108,"area":null},{"id":"2104.13906","title":"Reward (Mis)design for Autonomous Driving","created":"2021-04-28","cited_by_count":104,"area":"driving"},{"id":"2207.10050","title":"Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations","created":"2022-07-20","cited_by_count":89,"area":"offlinerl"},{"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":"2310.13639","title":"Contrastive Preference Learning: Learning from Human Feedback without RL","created":"2023-10-20","cited_by_count":79,"area":"alignment"},{"id":"2002.09089","title":"Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences","created":"2020-02-21","cited_by_count":73,"area":"offlinerl"},{"id":"2102.13185","title":"Off-Policy Imitation Learning from Observations","created":"2021-02-25","cited_by_count":70,"area":"offlinerl"},{"id":"2204.11134","title":"Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?","created":"2022-04-23","cited_by_count":70,"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":"2205.01663","title":"Adversarial Training for High-Stakes Reliability","created":"2022-05-03","cited_by_count":60,"area":null},{"id":"2106.12177","title":"Imitation Learning: Progress, Taxonomies and Challenges","created":"2021-06-23","cited_by_count":58,"area":"offlinerl"},{"id":"2401.16335","title":"Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF","created":"2024-01-29","cited_by_count":57,"area":"alignment"},{"id":"2301.01392","title":"Benchmarks and Algorithms for Offline Preference-Based Reward Learning","created":"2023-01-03","cited_by_count":56,"area":"alignment"},{"id":"2305.14816","title":"Provable Offline Preference-Based Reinforcement Learning","created":"2023-05-24","cited_by_count":55,"area":null},{"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":"2204.06601","title":"Causal Confusion and Reward Misidentification in Preference-Based Reward Learning","created":"2022-04-13","cited_by_count":53,"area":"alignment"},{"id":"2104.00053","title":"LazyDAgger: Reducing Context Switching in Interactive Imitation Learning","created":"2021-03-31","cited_by_count":51,"area":"offlinerl"},{"id":"2202.01288","title":"Imitation Learning by Estimating Expertise of Demonstrators","created":"2022-02-02","cited_by_count":50,"area":"offlinerl"},{"id":"2110.14754","title":"Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality","created":"2021-10-27","cited_by_count":44,"area":"offlinerl"},{"id":"2109.12750","title":"Learning Multimodal Rewards from Rankings","created":"2021-09-27","cited_by_count":41,"area":"alignment"},{"id":"2404.08495","title":"Dataset Reset Policy Optimization for RLHF","created":"2024-04-12","cited_by_count":41,"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":"2103.04529","title":"Self-Supervised Online Reward Shaping in Sparse-Reward Environments","created":"2021-03-08","cited_by_count":37,"area":null},{"id":"2309.06553","title":"Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL","created":"2023-09-13","cited_by_count":37,"area":"lr"},{"id":"2006.15061","title":"Intrinsic Reward Driven Imitation Learning via Generative Model","created":"2020-06-26","cited_by_count":35,"area":"offlinerl"},{"id":"2406.00888","title":"Aligning Language Models with Demonstrated Feedback","created":"2024-06-02","cited_by_count":34,"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":"2301.00355","title":"Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits","created":"2023-01-01","cited_by_count":27,"area":"lr"},{"id":"2403.01857","title":"Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences","created":"2024-03-04","cited_by_count":27,"area":"alignment"},{"id":"2405.15624","title":"Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learning","created":"2024-05-24","cited_by_count":27,"area":"alignment"},{"id":"2010.10181","title":"Robust Imitation Learning from Noisy Demonstrations","created":"2020-10-20","cited_by_count":26,"area":"offlinerl"},{"id":"2201.00012","title":"MORAL: Aligning AI with Human Norms through Multi-Objective Reinforced Active Learning","created":"2021-12-30","cited_by_count":25,"area":"alignment"},{"id":"2305.18505","title":"Provable Reward-Agnostic Preference-Based Reinforcement Learning","created":"2023-05-29","cited_by_count":25,"area":"alignment"},{"id":"2110.00284","title":"Learning Reward Functions from Scale Feedback","created":"2021-10-01","cited_by_count":24,"area":null},{"id":"2303.02569","title":"Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution Matching","created":"2023-03-05","cited_by_count":24,"area":"offlinerl"},{"id":"2102.12560","title":"PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning","created":"2021-02-24","cited_by_count":23,"area":null},{"id":"2210.08073","title":"Eliciting Compatible Demonstrations for Multi-Human Imitation Learning","created":"2022-10-14","cited_by_count":23,"area":"offlinerl"},{"id":"2311.14115","title":"A density estimation perspective on learning from pairwise human preferences","created":"2023-11-23","cited_by_count":23,"area":"alignment"},{"id":"2301.03652","title":"On The Fragility of Learned Reward Functions","created":"2023-01-09","cited_by_count":21,"area":"alignment"},{"id":"2301.04741","title":"Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models","created":"2023-01-11","cited_by_count":21,"area":null},{"id":"2211.06519","title":"The Expertise Problem: Learning from Specialized Feedback","created":"2022-11-12","cited_by_count":20,"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":"2207.03395","title":"Unified Learning from Demonstrations, Corrections, and Preferences during Physical Human-Robot Interaction","created":"2022-07-07","cited_by_count":19,"area":"offlinerl"},{"id":"2302.10342","title":"Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems","created":"2023-02-20","cited_by_count":19,"area":null},{"id":"2411.13451","title":"AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations","created":"2024-11-20","cited_by_count":19,"area":"mllm"},{"id":"1909.12200","title":"Scaling data-driven robotics with reward sketching and batch reinforcement learning","created":"2019-09-26","cited_by_count":18,"area":"offlinerl"},{"id":"2202.03481","title":"A Ranking Game for Imitation Learning","created":"2022-02-07","cited_by_count":18,"area":"offlinerl"},{"id":"2206.09670","title":"Benchmarking Constraint Inference in Inverse Reinforcement Learning","created":"2022-06-20","cited_by_count":18,"area":null},{"id":"2303.00638","title":"MEGA-DAgger: Imitation Learning with Multiple Imperfect Experts","created":"2023-03-01","cited_by_count":18,"area":"offlinerl"},{"id":"2503.03707","title":"Curating Demonstrations using Online Experience","created":"2025-03-05","cited_by_count":18,"area":null},{"id":"2506.11948","title":"SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies","created":"2025-06-13","cited_by_count":18,"area":"offlinerl"},{"id":"2107.09251","title":"Offline Preference-Based Apprenticeship Learning","created":"2021-07-20","cited_by_count":17,"area":"offlinerl"},{"id":"2212.01375","title":"Embedding Synthetic Off-Policy Experience for Autonomous Driving via Zero-Shot Curricula","created":"2022-12-02","cited_by_count":17,"area":"driving"},{"id":"2201.07082","title":"Inducing Structure in Reward Learning by Learning Features","created":"2022-01-18","cited_by_count":16,"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":"2308.03028","title":"Pre-Trained Large Language Models for Industrial Control","created":"2023-08-06","cited_by_count":16,"area":null},{"id":"2307.16348","title":"Rating-based Reinforcement Learning","created":"2023-07-30","cited_by_count":15,"area":null},{"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":"2501.08259","title":"FDPP: Fine-tune Diffusion Policy with Human Preference","created":"2025-01-14","cited_by_count":15,"area":"diffusion"},{"id":"2108.07259","title":"APReL: A Library for Active Preference-based Reward Learning Algorithms","created":"2021-08-16","cited_by_count":14,"area":null},{"id":"2301.00810","title":"SIRL: Similarity-based Implicit Representation Learning","created":"2023-01-02","cited_by_count":14,"area":null},{"id":"2310.07932","title":"What Matters to You? Towards Visual Representation Alignment for Robot Learning","created":"2023-10-11","cited_by_count":14,"area":"alignment"},{"id":"2401.08957","title":"Learning from Imperfect Demonstrations with Self-Supervision for Robotic Manipulation","created":"2024-01-17","cited_by_count":14,"area":null},{"id":"2407.15403","title":"Offline Imitation Learning Through Graph Search and Retrieval","created":"2024-07-22","cited_by_count":14,"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":"2410.22600","title":"Solving Minimum-Cost Reach Avoid using Reinforcement Learning","created":"2024-10-29","cited_by_count":14,"area":"deeprl"},{"id":"2107.05825","title":"Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks","created":"2021-07-13","cited_by_count":13,"area":null},{"id":"2302.13507","title":"Active Reward Learning from Online Preferences","created":"2023-02-27","cited_by_count":13,"area":"alignment"},{"id":"1909.06769","title":"VILD: Variational Imitation Learning with Diverse-quality Demonstrations","created":"2019-09-15","cited_by_count":12,"area":"offlinerl"},{"id":"2107.06317","title":"Inverse Contextual Bandits: Learning How Behavior Evolves over Time","created":"2021-07-13","cited_by_count":12,"area":null},{"id":"2403.12017","title":"Supervised Fine-Tuning as Inverse Reinforcement Learning","created":"2024-03-18","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":"2106.04240","title":"The Medkit-Learn(ing) Environment: Medical Decision Modelling through Simulation","created":"2021-06-08","cited_by_count":11,"area":null},{"id":"2106.06499","title":"Policy Gradient Bayesian Robust Optimization for Imitation Learning","created":"2021-06-11","cited_by_count":11,"area":"offlinerl"},{"id":"1907.03423","title":"On-Policy Robot Imitation Learning from a Converging Supervisor","created":"2019-07-08","cited_by_count":10,"area":"offlinerl"},{"id":"2201.12594","title":"Robust Imitation Learning from Corrupted Demonstrations","created":"2022-01-29","cited_by_count":10,"area":"offlinerl"},{"id":"2206.04477","title":"Receding Horizon Inverse Reinforcement Learning","created":"2022-06-09","cited_by_count":10,"area":"offlinerl"},{"id":"2210.04443","title":"Don't Copy the Teacher: Data and Model Challenges in Embodied Dialogue","created":"2022-10-10","cited_by_count":10,"area":null},{"id":"2310.08549","title":"Cross-Episodic Curriculum for Transformer Agents","created":"2023-10-12","cited_by_count":10,"area":null},{"id":"2310.18591","title":"Inverse Decision Modeling: Learning Interpretable Representations of Behavior","created":"2023-10-28","cited_by_count":10,"area":null},{"id":"2404.16779","title":"DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks","created":"2024-04-25","cited_by_count":10,"area":null},{"id":"2404.17906","title":"VIEW: Visual Imitation Learning with Waypoints","created":"2024-04-27","cited_by_count":10,"area":"offlinerl"},{"id":"2405.19697","title":"Bilevel reinforcement learning via the development of hyper-gradient without lower-level convexity","created":"2024-05-30","cited_by_count":10,"area":"deeprl"},{"id":"2201.04612","title":"Agent-Temporal Attention for Reward Redistribution in Episodic Multi-Agent Reinforcement Learning","created":"2022-01-12","cited_by_count":9,"area":null},{"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":"2405.01511","title":"D2PO: Discriminator-Guided DPO with Response Evaluation Models","created":"2024-05-02","cited_by_count":9,"area":"alignment"},{"id":"2502.21038","title":"Reward Learning from Multiple Feedback Types","created":"2025-02-28","cited_by_count":9,"area":"agents"},{"id":"2503.03921","title":"CREStE: Scalable Mapless Navigation with Internet Scale Priors and Counterfactual Guidance","created":"2025-03-05","cited_by_count":9,"area":null}],"next_cursor":"100"}