{"total":23,"rows":[{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590,"area":"offlinerl"},{"id":"2202.05607","title":"Online Decision Transformer","created":"2022-02-11","cited_by_count":196,"area":"offlinerl"},{"id":"2009.07253","title":"Autoregressive Knowledge Distillation through Imitation Learning","created":"2020-09-15","cited_by_count":74,"area":"offlinerl"},{"id":"2009.07839","title":"Text Generation by Learning from Demonstrations","created":"2020-09-16","cited_by_count":64,"area":"offlinerl"},{"id":"2102.11492","title":"DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning","created":"2021-02-23","cited_by_count":48,"area":"offlinerl"},{"id":"2206.08569","title":"Bootstrapped Transformer for Offline Reinforcement Learning","created":"2022-06-17","cited_by_count":37,"area":"offlinerl"},{"id":"2605.16826","title":"Decoupling KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM Distillation","created":"2026-05-16","cited_by_count":20,"area":"offlinerl"},{"id":"2402.07876","title":"Policy Improvement using Language Feedback Models","created":"2024-02-12","cited_by_count":16,"area":"offlinerl"},{"id":"2005.12801","title":"Active Imitation Learning with Noisy Guidance","created":"2020-05-26","cited_by_count":15,"area":"offlinerl"},{"id":"2203.08619","title":"An Independently Learnable Hierarchical Model for Bilateral Control-Based Imitation Learning Applications","created":"2022-03-16","cited_by_count":14,"area":"offlinerl"},{"id":"2107.03851","title":"Imitation by Predicting Observations","created":"2021-07-08","cited_by_count":13,"area":"offlinerl"},{"id":"2306.09712","title":"Semi-Offline Reinforcement Learning for Optimized Text Generation","created":"2023-06-16","cited_by_count":12,"area":"offlinerl"},{"id":"1908.10835","title":"An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation","created":"2019-08-28","cited_by_count":11,"area":"offlinerl"},{"id":"2011.06192","title":"Motion Generation Using Bilateral Control-Based Imitation Learning with Autoregressive Learning","created":"2020-11-12","cited_by_count":11,"area":"offlinerl"},{"id":"2002.04306","title":"Learning Coupled Policies for Simultaneous Machine Translation using Imitation Learning","created":"2020-02-11","cited_by_count":10,"area":"offlinerl"},{"id":"1811.00512","title":"Learning Beam Search Policies via Imitation Learning","created":"2018-11-01","cited_by_count":9,"area":"offlinerl"},{"id":"2510.06499","title":"Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels","created":"2025-10-07","cited_by_count":8,"area":"offlinerl"},{"id":"2209.12868","title":"On Efficient Online Imitation Learning via Classification","created":"2022-09-26","cited_by_count":5,"area":"offlinerl"},{"id":"2001.06944","title":"Nested-Wasserstein Self-Imitation Learning for Sequence Generation","created":"2020-01-20","cited_by_count":3,"area":"offlinerl"},{"id":"2109.04114","title":"Fixing exposure bias with imitation learning needs powerful oracles","created":"2021-09-09","cited_by_count":3,"area":"offlinerl"},{"id":"2512.23097","title":"A Note on Hybrid Online Reinforcement and Imitation Learning for LLMs: Formulations and Algorithms","created":"2025-12-28","cited_by_count":3,"area":"offlinerl"},{"id":"2007.00425","title":"Interaction-limited Inverse Reinforcement Learning","created":"2020-07-01","cited_by_count":0,"area":"offlinerl"},{"id":"2110.08963","title":"SS-MAIL: Self-Supervised Multi-Agent Imitation Learning","created":"2021-10-18","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}