{"total":56,"rows":[{"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":"2306.08543","title":"MiniLLM: On-Policy Distillation of Large Language Models","created":"2023-06-14","cited_by_count":139,"area":"distill"},{"id":"2402.00782","title":"Dense Reward for Free in Reinforcement Learning from Human Feedback","created":"2024-02-01","cited_by_count":78,"area":"alignment"},{"id":"2106.03207","title":"Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage","created":"2021-06-06","cited_by_count":26,"area":"offlinerl"},{"id":"2209.10968","title":"Proximal Point Imitation Learning","created":"2022-09-22","cited_by_count":26,"area":"offlinerl"},{"id":"2302.07457","title":"When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning","created":"2023-02-15","cited_by_count":26,"area":"wm"},{"id":"2302.04782","title":"CLARE: Conservative Model-Based Reward Learning for Offline Inverse Reinforcement Learning","created":"2023-02-09","cited_by_count":20,"area":"offlinerl"},{"id":"2206.09670","title":"Benchmarking Constraint Inference in Inverse Reinforcement Learning","created":"2022-06-20","cited_by_count":18,"area":null},{"id":"2203.08057","title":"POETREE: Interpretable Policy Learning with Adaptive Decision Trees","created":"2022-03-15","cited_by_count":14,"area":null},{"id":"2405.17476","title":"How to Leverage Diverse Demonstrations in Offline Imitation Learning","created":"2024-05-24","cited_by_count":12,"area":"offlinerl"},{"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":"2210.08708","title":"Teacher Forcing Recovers Reward Functions for Text Generation","created":"2022-10-17","cited_by_count":11,"area":null},{"id":"2305.11290","title":"Massively Scalable Inverse Reinforcement Learning in Google Maps","created":"2023-05-18","cited_by_count":11,"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":"2311.13870","title":"Multi-intention Inverse Q-learning for Interpretable Behavior Representation","created":"2023-11-23","cited_by_count":9,"area":"offlinerl"},{"id":"2305.14608","title":"Inverse Reinforcement Learning with the Average Reward Criterion","created":"2023-05-24","cited_by_count":8,"area":"offlinerl"},{"id":"2502.14272","title":"Capturing Nuanced Preferences: Preference-Aligned Distillation for Small Language Models","created":"2025-02-20","cited_by_count":8,"area":"lr"},{"id":"2305.02857","title":"Maximum Causal Entropy Inverse Constrained Reinforcement Learning","created":"2023-05-04","cited_by_count":7,"area":null},{"id":"2410.15612","title":"In-Trajectory Inverse Reinforcement Learning: Learn Incrementally Before An Ongoing Trajectory Terminates","created":"2024-10-21","cited_by_count":7,"area":"offlinerl"},{"id":"2203.07338","title":"Inverse Online Learning: Understanding Non-Stationary and Reactionary Policies","created":"2022-03-14","cited_by_count":6,"area":null},{"id":"2403.15341","title":"Collaborative AI Teaming in Unknown Environments via Active Goal Deduction","created":"2024-03-22","cited_by_count":6,"area":null},{"id":"2405.17477","title":"OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning","created":"2024-05-24","cited_by_count":6,"area":"offlinerl"},{"id":"2410.02664","title":"Grounded Answers for Multi-agent Decision-making Problem through Generative World Model","created":"2024-10-03","cited_by_count":6,"area":"wm"},{"id":"2306.08232","title":"Curricular Subgoals for Inverse Reinforcement Learning","created":"2023-06-14","cited_by_count":5,"area":"offlinerl"},{"id":"2110.11130","title":"Inverse Optimal Control Adapted to the Noise Characteristics of the Human Sensorimotor System","created":"2021-10-21","cited_by_count":4,"area":null},{"id":"2208.04919","title":"Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience","created":"2022-08-09","cited_by_count":4,"area":"offlinerl"},{"id":"2210.14972","title":"Environment Design for Inverse Reinforcement Learning","created":"2022-10-26","cited_by_count":4,"area":"offlinerl"},{"id":"2407.10971","title":"Walking the Values in Bayesian Inverse Reinforcement Learning","created":"2024-07-15","cited_by_count":4,"area":"offlinerl"},{"id":"2410.03924","title":"Online Control-Informed Learning","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2411.07362","title":"Factorised Active Inference for Strategic Multi-Agent Interactions","created":"2024-11-11","cited_by_count":4,"area":null},{"id":"2411.09341","title":"Approximated Variational Bayesian Inverse Reinforcement Learning for Large Language Model Alignment","created":"2024-11-14","cited_by_count":4,"area":"alignment"},{"id":"2211.06138","title":"Practical Approaches for Fair Learning with Multitype and Multivariate Sensitive Attributes","created":"2022-11-11","cited_by_count":3,"area":null},{"id":"2303.01440","title":"Programmatic Imitation Learning from Unlabeled and Noisy Demonstrations","created":"2023-03-02","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":"2409.12500","title":"LLMR: Knowledge Distillation with a Large Language Model-Induced Reward","created":"2024-09-19","cited_by_count":3,"area":"distill"},{"id":"2410.03847","title":"Enhancing Inverse Reinforcement Learning through Encoding Dynamic Information in Reward Shaping","created":"2024-10-04","cited_by_count":3,"area":"offlinerl"},{"id":"2210.05320","title":"Synthetic Model Combination: An Instance-wise Approach to Unsupervised Ensemble Learning","created":"2022-10-11","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":"2410.16517","title":"RGMDT: Return-Gap-Minimizing Decision Tree Extraction in Non-Euclidean Metric Space","created":"2024-10-21","cited_by_count":2,"area":"deeprl"},{"id":"2602.20527","title":"A Generalized Apprenticeship Learning Framework for Capturing Evolving Student Pedagogical Strategies","created":"2026-02-24","cited_by_count":2,"area":"deeprl"},{"id":"2305.03987","title":"Replicating Complex Dialogue Policy of Humans via Offline Imitation Learning with Supervised Regularization","created":"2023-05-06","cited_by_count":1,"area":"offlinerl"},{"id":"2311.07426","title":"Optimising Human-AI Collaboration by Learning Convincing Explanations","created":"2023-11-13","cited_by_count":1,"area":null},{"id":"2409.15963","title":"Provably Efficient Exploration in Inverse Constrained Reinforcement Learning","created":"2024-09-24","cited_by_count":1,"area":"deeprl"},{"id":"2508.03693","title":"PAC Apprenticeship Learning with Bayesian Active Inverse Reinforcement Learning","created":"2025-08-05","cited_by_count":1,"area":"offlinerl"},{"id":"2602.12674","title":"$\\mathcal{X}$-KD: General Experiential Knowledge Distillation for Large Language Models","created":"2026-02-13","cited_by_count":1,"area":"distill"},{"id":"2206.05521","title":"Model-based Offline Imitation Learning with Non-expert Data","created":"2022-06-11","cited_by_count":0,"area":"offlinerl"},{"id":"2209.13489","title":"Reward Learning using Structural Motifs in Inverse Reinforcement Learning","created":"2022-09-25","cited_by_count":0,"area":"offlinerl"},{"id":"2303.06827","title":"Kernel Density Bayesian Inverse Reinforcement Learning","created":"2023-03-13","cited_by_count":0,"area":"offlinerl"},{"id":"2311.03698","title":"A Novel Variational Lower Bound for Inverse Reinforcement Learning","created":"2023-11-07","cited_by_count":0,"area":"offlinerl"},{"id":"2402.02608","title":"Accelerating Inverse Reinforcement Learning with Expert Bootstrapping","created":"2024-02-04","cited_by_count":0,"area":"offlinerl"},{"id":"2402.02616","title":"The Virtues of Pessimism in Inverse Reinforcement Learning","created":"2024-02-04","cited_by_count":0,"area":"offlinerl"},{"id":"2412.02931","title":"Inverse Delayed Reinforcement Learning","created":"2024-12-04","cited_by_count":0,"area":"offlinerl"},{"id":"2510.03013","title":"Distributional Inverse Reinforcement Learning","created":"2025-10-03","cited_by_count":0,"area":"offlinerl"},{"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":"2603.22083","title":"A Context Engineering Framework for Improving Enterprise AI Agents based on Digital-Twin MDP","created":"2026-03-23","cited_by_count":0,"area":"agents"},{"id":"2608.16888","title":"Q-based Variational Inverse Reinforcement Learning","created":"2026-08-17","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}