{"total":123,"rows":[{"id":"2301.10677","title":"Imitating Human Behaviour with Diffusion Models","created":"2023-01-25","cited_by_count":263,"area":"diffusion"},{"id":"1911.02256","title":"A Divergence Minimization Perspective on Imitation Learning Methods","created":"2019-11-06","cited_by_count":190,"area":"offlinerl"},{"id":"1912.05032","title":"Imitation Learning via Off-Policy Distribution Matching","created":"2019-12-10","cited_by_count":183,"area":"offlinerl"},{"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":"2009.05990","title":"Toward the Fundamental Limits of Imitation Learning","created":"2020-09-13","cited_by_count":96,"area":"offlinerl"},{"id":"2203.15103","title":"Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions","created":"2022-03-28","cited_by_count":89,"area":null},{"id":"2103.03236","title":"Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap","created":"2021-03-04","cited_by_count":81,"area":"offlinerl"},{"id":"2306.02437","title":"Data Quality in Imitation Learning","created":"2023-06-04","cited_by_count":75,"area":"offlinerl"},{"id":"1911.10947","title":"State Alignment-based Imitation Learning","created":"2019-11-21","cited_by_count":73,"area":"offlinerl"},{"id":"2408.16673","title":"Preserving Diversity in Supervised Fine-Tuning of Large Language Models","created":"2024-08-29","cited_by_count":70,"area":null},{"id":"2011.04709","title":"f-IRL: Inverse Reinforcement Learning via State Marginal Matching","created":"2020-11-09","cited_by_count":67,"area":"offlinerl"},{"id":"2206.03023","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":"2310.05905","title":"TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models","created":"2023-10-09","cited_by_count":53,"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":"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":"2510.09459","title":"Failure Prediction at Runtime for Generative Robot Policies","created":"2025-10-10","cited_by_count":42,"area":"diffusion"},{"id":"2004.09395","title":"Energy-Based Imitation Learning","created":"2020-04-20","cited_by_count":40,"area":"offlinerl"},{"id":"2011.06719","title":"Grasping with Chopsticks: Combating Covariate Shift in Model-free Imitation Learning for Fine Manipulation","created":"2020-11-13","cited_by_count":38,"area":"offlinerl"},{"id":"2302.13335","title":"Diffusion Model-Augmented Behavioral Cloning","created":"2023-02-26","cited_by_count":38,"area":"diffusion"},{"id":"2008.09167","title":"Imitation Learning with Sinkhorn Distances","created":"2020-08-20","cited_by_count":30,"area":"offlinerl"},{"id":"2310.12972","title":"CCIL: Continuity-based Data Augmentation for Corrective Imitation Learning","created":"2023-10-19","cited_by_count":29,"area":"offlinerl"},{"id":"2103.05910","title":"Learning from Imperfect Demonstrations from Agents with Varying Dynamics","created":"2021-03-10","cited_by_count":27,"area":"offlinerl"},{"id":"2209.10968","title":"Proximal Point Imitation Learning","created":"2022-09-22","cited_by_count":26,"area":"offlinerl"},{"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":"2202.13536","title":"LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation","created":"2022-02-28","cited_by_count":23,"area":null},{"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":"2405.07162","title":"Learning Reward for Robot Skills Using Large Language Models via Self-Alignment","created":"2024-05-12","cited_by_count":20,"area":null},{"id":"2104.02180","title":"AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control","created":"2021-04-05","cited_by_count":18,"area":null},{"id":"2202.03481","title":"A Ranking Game for Imitation Learning","created":"2022-02-07","cited_by_count":18,"area":"offlinerl"},{"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":"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":"2202.02468","title":"Rethinking ValueDice: Does It Really Improve Performance?","created":"2022-02-05","cited_by_count":15,"area":"offlinerl"},{"id":"2211.11603","title":"Model-based Trajectory Stitching for Improved Offline Reinforcement Learning","created":"2022-11-21","cited_by_count":15,"area":"offlinerl"},{"id":"2106.03155","title":"SoftDICE for Imitation Learning: Rethinking Off-policy Distribution Matching","created":"2021-06-06","cited_by_count":14,"area":"offlinerl"},{"id":"2110.06539","title":"On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning","created":"2021-10-13","cited_by_count":14,"area":"offlinerl"},{"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":"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":"2306.14534","title":"CEIL: Generalized Contextual Imitation Learning","created":"2023-06-26","cited_by_count":13,"area":"offlinerl"},{"id":"2411.17764","title":"PROGRESSOR: A Perceptually Guided Reward Estimator with Self-Supervised Online Refinement","created":"2024-11-26","cited_by_count":13,"area":"deeprl"},{"id":"2102.12948","title":"Provably Breaking the Quadratic Error Compounding Barrier in Imitation Learning, Optimally","created":"2021-02-25","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":"2505.04961","title":"Physics-Based Motion Imitation with Adversarial Differential Discriminators","created":"2025-05-08","cited_by_count":12,"area":null},{"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":"2204.11446","title":"Imitation Learning from Observations under Transition Model Disparity","created":"2022-04-25","cited_by_count":11,"area":"offlinerl"},{"id":"2305.11290","title":"Massively Scalable Inverse Reinforcement Learning in Google Maps","created":"2023-05-18","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":"2206.04477","title":"Receding Horizon Inverse Reinforcement Learning","created":"2022-06-09","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":"2310.18591","title":"Inverse Decision Modeling: Learning Interpretable Representations of Behavior","created":"2023-10-28","cited_by_count":10,"area":null},{"id":"2010.03691","title":"Regularized Inverse Reinforcement Learning","created":"2020-10-07","cited_by_count":9,"area":"offlinerl"},{"id":"2212.04280","title":"Model-based trajectory stitching for improved behavioural cloning and its applications","created":"2022-12-08","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":"2105.12991","title":"Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization","created":"2021-05-27","cited_by_count":8,"area":null},{"id":"2310.01632","title":"Imitation Learning from Observation through Optimal Transport","created":"2023-10-02","cited_by_count":7,"area":"offlinerl"},{"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":"2205.01906","title":"ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters","created":"2022-05-04","cited_by_count":6,"area":null},{"id":"2411.00610","title":"Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation","created":"2024-11-01","cited_by_count":6,"area":"offlinerl"},{"id":"2209.12868","title":"On Efficient Online Imitation Learning via Classification","created":"2022-09-26","cited_by_count":5,"area":"offlinerl"},{"id":"2310.14092","title":"Learning Reward for Physical Skills using Large Language Model","created":"2023-10-21","cited_by_count":5,"area":null},{"id":"2404.08513","title":"Adversarial Imitation Learning via Boosting","created":"2024-04-12","cited_by_count":5,"area":"offlinerl"},{"id":"2509.21172","title":"Inverse Reinforcement Learning with Just Classification and a Few Regressions","created":"2025-09-25","cited_by_count":5,"area":"offlinerl"},{"id":"2510.19495","title":"Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learning","created":"2025-10-22","cited_by_count":5,"area":"offlinerl"},{"id":"2602.04417","title":"EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL","created":"2026-02-04","cited_by_count":5,"area":"lr"},{"id":"2006.07777","title":"Active Imitation Learning from Multiple Non-Deterministic Teachers: Formulation, Challenges, and Algorithms","created":"2020-06-14","cited_by_count":4,"area":"offlinerl"},{"id":"2411.07595","title":"Entropy Controllable Direct Preference Optimization","created":"2024-11-12","cited_by_count":4,"area":"alignment"},{"id":"2504.13368","title":"An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2605.15417","title":"$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2101.00186","title":"Inverse reinforcement learning for autonomous navigation via differentiable semantic mapping and planning","created":"2021-01-01","cited_by_count":3,"area":"offlinerl"},{"id":"2112.06054","title":"Deterministic and Discriminative Imitation (D2-Imitation): Revisiting Adversarial Imitation for Sample Efficiency","created":"2021-12-11","cited_by_count":3,"area":"offlinerl"},{"id":"2206.02095","title":"ARC - Actor Residual Critic for Adversarial Imitation Learning","created":"2022-06-05","cited_by_count":3,"area":"offlinerl"},{"id":"2302.06271","title":"Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning","created":"2023-02-13","cited_by_count":3,"area":"offlinerl"},{"id":"2310.07143","title":"Imitation Learning from Purified Demonstrations","created":"2023-10-11","cited_by_count":3,"area":"offlinerl"},{"id":"2408.09125","title":"Markov Balance Satisfaction Improves Performance in Strictly Batch Offline Imitation Learning","created":"2024-08-17","cited_by_count":3,"area":"offlinerl"},{"id":"2501.02330","title":"SR-Reward: Taking The Path More Traveled","created":"2025-01-04","cited_by_count":3,"area":"offlinerl"},{"id":"2505.10760","title":"Counterfactual Behavior Cloning: Offline Imitation Learning from Imperfect Human Demonstrations","created":"2025-05-16","cited_by_count":3,"area":"offlinerl"},{"id":"2106.01777","title":"LiMIIRL: Lightweight Multiple-Intent Inverse Reinforcement Learning","created":"2021-06-03","cited_by_count":2,"area":"offlinerl"},{"id":"2301.11461","title":"Learning to Generate All Feasible Actions","created":"2023-01-26","cited_by_count":2,"area":null},{"id":"2308.12573","title":"Conditional Kernel Imitation Learning for Continuous State Environments","created":"2023-08-24","cited_by_count":2,"area":"offlinerl"},{"id":"2402.01057","title":"Expert Proximity as Surrogate Rewards for Single Demonstration Imitation Learning","created":"2024-02-01","cited_by_count":2,"area":"offlinerl"},{"id":"2404.03382","title":"DIDA: Denoised Imitation Learning based on Domain Adaptation","created":"2024-04-04","cited_by_count":2,"area":"offlinerl"},{"id":"2412.07057","title":"Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning","created":"2024-12-09","cited_by_count":2,"area":"offlinerl"},{"id":"2506.04716","title":"Learning dissection trajectories from expert surgical videos via imitation learning with equivariant diffusion","created":"2025-06-05","cited_by_count":2,"area":"diffusion"},{"id":"2203.03432","title":"Learning Solution Manifolds for Control Problems via Energy Minimization","created":"2022-03-07","cited_by_count":1,"area":"offlinerl"},{"id":"2301.11476","title":"Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence","created":"2023-01-27","cited_by_count":1,"area":null},{"id":"2309.14829","title":"A Structured Prediction Approach for Robot Imitation Learning","created":"2023-09-26","cited_by_count":1,"area":"offlinerl"},{"id":"2312.16860","title":"Agnostic Interactive Imitation Learning: New Theory and Practical Algorithms","created":"2023-12-28","cited_by_count":1,"area":"offlinerl"},{"id":"2503.05229","title":"Discrete Contrastive Learning for Diffusion Policies in Autonomous Driving","created":"2025-03-07","cited_by_count":1,"area":"diffusion"},{"id":"2510.00922","title":"On Discovering Algorithms for Adversarial Imitation Learning","created":"2025-10-01","cited_by_count":1,"area":"offlinerl"},{"id":"2605.01778","title":"Adversarial Imitation Learning with General Function Approximation: Theoretical Analysis and Practical Algorithms","created":"2026-05-03","cited_by_count":1,"area":"offlinerl"},{"id":"2606.27475","title":"Support-Constrained RL Enables Real-World Policy Improvement without Real-World Experience","created":"2026-06-25","cited_by_count":1,"area":null}],"next_cursor":"100"}