{"total":190,"rows":[{"id":"2301.10677","title":"Imitating Human Behaviour with Diffusion Models","created":"2023-01-25","cited_by_count":263,"area":"diffusion"},{"id":"2006.04678","title":"Primal Wasserstein Imitation Learning","created":"2020-06-08","cited_by_count":121,"area":"offlinerl"},{"id":"2302.08215","title":"Aligning Language Models with Preferences through f-divergence Minimization","created":"2023-02-16","cited_by_count":120,"area":"alignment"},{"id":"2111.10364","title":"Generalized Decision Transformer for Offline Hindsight Information Matching","created":"2021-11-19","cited_by_count":106,"area":"offlinerl"},{"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":"2106.00672","title":"What Matters for Adversarial Imitation Learning?","created":"2021-06-01","cited_by_count":70,"area":"offlinerl"},{"id":"2011.04709","title":"f-IRL: Inverse Reinforcement Learning via State Marginal Matching","created":"2020-11-09","cited_by_count":67,"area":"offlinerl"},{"id":"2206.15469","title":"Watch and Match: Supercharging Imitation with Regularized Optimal Transport","created":"2022-06-30","cited_by_count":67,"area":"offlinerl"},{"id":"2206.03023","title":"How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression","created":"2022-06-07","cited_by_count":66,"area":"offlinerl"},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66,"area":"wm"},{"id":"2106.03787","title":"Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint","created":"2021-06-07","cited_by_count":56,"area":null},{"id":"2006.14154","title":"Strictly Batch Imitation Learning by Energy-based Distribution Matching","created":"2020-06-25","cited_by_count":54,"area":"offlinerl"},{"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":"2006.06412","title":"Modeling Human Driving Behavior through Generative Adversarial Imitation Learning","created":"2020-06-10","cited_by_count":45,"area":"offlinerl"},{"id":"2102.10769","title":"MobILE: Model-Based Imitation Learning From Observation Alone","created":"2021-02-22","cited_by_count":44,"area":"offlinerl"},{"id":"2202.02433","title":"Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching","created":"2022-02-04","cited_by_count":43,"area":"offlinerl"},{"id":"2107.08829","title":"Visual Adversarial Imitation Learning using Variational Models","created":"2021-07-16","cited_by_count":42,"area":"offlinerl"},{"id":"2107.08285","title":"Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences","created":"2021-07-17","cited_by_count":41,"area":null},{"id":"2004.09395","title":"Energy-Based Imitation Learning","created":"2020-04-20","cited_by_count":40,"area":"offlinerl"},{"id":"2105.13345","title":"Adversarial Intrinsic Motivation for Reinforcement Learning","created":"2021-05-27","cited_by_count":40,"area":"offlinerl"},{"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":"2312.10584","title":"Policy Optimization in RLHF: The Impact of Out-of-preference Data","created":"2023-12-17","cited_by_count":35,"area":"alignment"},{"id":"2303.01488","title":"Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning","created":"2023-03-02","cited_by_count":34,"area":null},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2101.07012","title":"Regularized Policies are Reward Robust","created":"2021-01-18","cited_by_count":32,"area":null},{"id":"2008.09167","title":"Imitation Learning with Sinkhorn Distances","created":"2020-08-20","cited_by_count":30,"area":"offlinerl"},{"id":"2202.01511","title":"Challenging Common Assumptions in Convex Reinforcement Learning","created":"2022-02-03","cited_by_count":30,"area":"offlinerl"},{"id":"2303.00599","title":"LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning","created":"2023-03-01","cited_by_count":29,"area":"offlinerl"},{"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":"2210.08863","title":"You Only Live Once: Single-Life Reinforcement Learning","created":"2022-10-17","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":"2311.01394","title":"Learning Realistic Traffic Agents in Closed-loop","created":"2023-11-02","cited_by_count":24,"area":null},{"id":"2006.13258","title":"Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization","created":"2020-06-23","cited_by_count":22,"area":"offlinerl"},{"id":"2110.10149","title":"Continuous Control with Action Quantization from Demonstrations","created":"2021-10-19","cited_by_count":22,"area":null},{"id":"2205.05212","title":"A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning","created":"2022-05-11","cited_by_count":22,"area":null},{"id":"2305.16498","title":"Coherent Soft Imitation Learning","created":"2023-05-25","cited_by_count":22,"area":"offlinerl"},{"id":"2111.07447","title":"Learning Multi-Stage Tasks with One Demonstration via Self-Replay","created":"2021-11-14","cited_by_count":21,"area":"offlinerl"},{"id":"2302.03086","title":"DITTO: Offline Imitation Learning with World Models","created":"2023-02-06","cited_by_count":21,"area":"wm"},{"id":"2311.02013","title":"SMORE: Score Models for Offline Goal-Conditioned Reinforcement Learning","created":"2023-11-03","cited_by_count":21,"area":"offlinerl"},{"id":"2409.01369","title":"Imitating Language via Scalable Inverse Reinforcement Learning","created":"2024-09-02","cited_by_count":21,"area":"offlinerl"},{"id":"2010.01207","title":"$f$-GAIL: Learning $f$-Divergence for Generative Adversarial Imitation Learning","created":"2020-10-02","cited_by_count":20,"area":"offlinerl"},{"id":"2402.13777","title":"Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions","created":"2024-02-21","cited_by_count":20,"area":"offlinerl"},{"id":"2106.05530","title":"Adversarial Option-Aware Hierarchical Imitation Learning","created":"2021-06-10","cited_by_count":19,"area":"offlinerl"},{"id":"2109.05439","title":"Concave Utility Reinforcement Learning with Zero-Constraint Violations","created":"2021-09-12","cited_by_count":19,"area":null},{"id":"2410.14250","title":"Vision-Language Navigation with Energy-Based Policy","created":"2024-10-18","cited_by_count":19,"area":null},{"id":"2202.03481","title":"A Ranking Game for Imitation Learning","created":"2022-02-07","cited_by_count":18,"area":"offlinerl"},{"id":"2306.01854","title":"Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space","created":"2023-06-02","cited_by_count":18,"area":null},{"id":"2312.06348","title":"DiffAIL: Diffusion Adversarial Imitation Learning","created":"2023-12-11","cited_by_count":18,"area":"diffusion"},{"id":"2008.03525","title":"Non-Adversarial Imitation Learning and its Connections to Adversarial Methods","created":"2020-08-08","cited_by_count":17,"area":"offlinerl"},{"id":"2105.12034","title":"Hyperparameter Selection for Imitation Learning","created":"2021-05-25","cited_by_count":17,"area":"offlinerl"},{"id":"2108.04763","title":"Imitation Learning by Reinforcement Learning","created":"2021-08-10","cited_by_count":17,"area":"offlinerl"},{"id":"2306.14079","title":"Fighting Uncertainty with Gradients: Offline Reinforcement Learning via Diffusion Score Matching","created":"2023-06-24","cited_by_count":17,"area":"offlinerl"},{"id":"2507.00018","title":"Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections","created":"2025-06-15","cited_by_count":17,"area":"alignment"},{"id":"2302.00965","title":"Visual Imitation Learning with Patch Rewards","created":"2023-02-02","cited_by_count":16,"area":"offlinerl"},{"id":"2306.06563","title":"Provably Efficient Adversarial Imitation Learning with Unknown Transitions","created":"2023-06-11","cited_by_count":16,"area":"offlinerl"},{"id":"2410.13855","title":"Diffusing States and Matching Scores: A New Framework for Imitation Learning","created":"2024-10-17","cited_by_count":16,"area":"diffusion"},{"id":"2103.17258","title":"Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning","created":"2021-03-31","cited_by_count":15,"area":null},{"id":"2106.01404","title":"Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning","created":"2021-06-02","cited_by_count":15,"area":null},{"id":"2109.04307","title":"OPIRL: Sample Efficient Off-Policy Inverse Reinforcement Learning via Distribution Matching","created":"2021-09-09","cited_by_count":15,"area":"offlinerl"},{"id":"2202.02468","title":"Rethinking ValueDice: Does It Really Improve Performance?","created":"2022-02-05","cited_by_count":15,"area":"offlinerl"},{"id":"2306.16884","title":"Policy Space Diversity for Non-Transitive Games","created":"2023-06-29","cited_by_count":15,"area":null},{"id":"2311.01489","title":"Invariant Causal Imitation Learning for Generalizable Policies","created":"2023-11-02","cited_by_count":15,"area":"offlinerl"},{"id":"2407.09905","title":"Global Reinforcement Learning: Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods","created":"2024-07-13","cited_by_count":15,"area":"deeprl"},{"id":"2106.03155","title":"SoftDICE for Imitation Learning: Rethinking Off-policy Distribution Matching","created":"2021-06-06","cited_by_count":14,"area":"offlinerl"},{"id":"2106.04958","title":"Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games","created":"2021-06-09","cited_by_count":14,"area":null},{"id":"2310.06794","title":"$f$-Policy Gradients: A General Framework for Goal Conditioned RL using $f$-Divergences","created":"2023-10-10","cited_by_count":14,"area":null},{"id":"2402.03807","title":"SEABO: A Simple Search-Based Method for Offline Imitation Learning","created":"2024-02-06","cited_by_count":14,"area":"offlinerl"},{"id":"2006.13506","title":"When Will Generative Adversarial Imitation Learning Algorithms Attain Global Convergence","created":"2020-06-24","cited_by_count":13,"area":"offlinerl"},{"id":"2107.03851","title":"Imitation by Predicting Observations","created":"2021-07-08","cited_by_count":13,"area":"offlinerl"},{"id":"2208.01899","title":"Understanding Adversarial Imitation Learning in Small Sample Regime: A Stage-coupled Analysis","created":"2022-08-03","cited_by_count":13,"area":"offlinerl"},{"id":"2205.09251","title":"IL-flOw: Imitation Learning from Observation using Normalizing Flows","created":"2022-05-19","cited_by_count":12,"area":"offlinerl"},{"id":"2305.00303","title":"A Coupled Flow Approach to Imitation Learning","created":"2023-04-29","cited_by_count":12,"area":"offlinerl"},{"id":"2310.05422","title":"Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement Learning","created":"2023-10-09","cited_by_count":12,"area":"offlinerl"},{"id":"2403.12017","title":"Supervised Fine-Tuning as Inverse Reinforcement Learning","created":"2024-03-18","cited_by_count":12,"area":"alignment"},{"id":"2110.04686","title":"Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization","created":"2021-10-10","cited_by_count":11,"area":null},{"id":"2309.17371","title":"Adversarial Imitation Learning from Visual Observations using Latent Information","created":"2023-09-29","cited_by_count":11,"area":"offlinerl"},{"id":"2405.13193","title":"Efficient Imitation Learning with Conservative World Models","created":"2024-05-21","cited_by_count":11,"area":"wm"},{"id":"2112.14004","title":"Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations","created":"2021-12-28","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":"2306.10695","title":"SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models","created":"2023-06-19","cited_by_count":10,"area":"offlinerl"},{"id":"2306.14799","title":"On Imitation in Mean-field Games","created":"2023-06-26","cited_by_count":10,"area":"offlinerl"},{"id":"2310.02505","title":"Learning to Reach Goals via Diffusion","created":"2023-10-04","cited_by_count":10,"area":"diffusion"},{"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":"2406.08805","title":"A Dual Approach to Imitation Learning from Observations with Offline Datasets","created":"2024-06-13","cited_by_count":10,"area":"offlinerl"},{"id":"2010.03691","title":"Regularized Inverse Reinforcement Learning","created":"2020-10-07","cited_by_count":9,"area":"offlinerl"},{"id":"2108.01867","title":"A Pragmatic Look at Deep Imitation Learning","created":"2021-08-04","cited_by_count":9,"area":"offlinerl"},{"id":"2309.08571","title":"A Bayesian Approach to Robust Inverse Reinforcement Learning","created":"2023-09-15","cited_by_count":9,"area":"offlinerl"},{"id":"2407.12792","title":"Visually Robust Adversarial Imitation Learning from Videos with Contrastive Learning","created":"2024-06-18","cited_by_count":9,"area":"offlinerl"},{"id":"2310.01632","title":"Imitation Learning from Observation through Optimal Transport","created":"2023-10-02","cited_by_count":7,"area":"offlinerl"},{"id":"2412.05718","title":"RLZero: Direct Policy Inference from Language Without In-Domain Supervision","created":"2024-12-07","cited_by_count":7,"area":null},{"id":"2507.13158","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","created":"2025-07-17","cited_by_count":7,"area":"alignment"},{"id":"2008.07284","title":"Forward and inverse reinforcement learning sharing network weights and hyperparameters","created":"2020-08-17","cited_by_count":6,"area":"offlinerl"},{"id":"2202.04332","title":"Imitation Learning by State-Only Distribution Matching","created":"2022-02-09","cited_by_count":6,"area":"offlinerl"},{"id":"2205.08716","title":"No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL","created":"2022-05-18","cited_by_count":6,"area":null},{"id":"2208.00088","title":"Improved Policy Optimization for Online Imitation Learning","created":"2022-07-29","cited_by_count":6,"area":"offlinerl"},{"id":"2210.08121","title":"Inferring Versatile Behavior from Demonstrations by Matching Geometric Descriptors","created":"2022-10-17","cited_by_count":6,"area":"offlinerl"},{"id":"2210.11201","title":"Robust Imitation via Mirror Descent Inverse Reinforcement Learning","created":"2022-10-20","cited_by_count":6,"area":"offlinerl"}],"next_cursor":"100"}