{"total":26,"rows":[{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345,"area":"offlinerl"},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214,"area":"offlinerl"},{"id":"2102.06203","title":"Proof Artifact Co-training for Theorem Proving with Language Models","created":"2021-02-11","cited_by_count":132,"area":"offlinerl"},{"id":"2201.13425","title":"Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning","created":"2022-01-31","cited_by_count":96,"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":"2210.03112","title":"A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning","created":"2022-10-06","cited_by_count":60,"area":"offlinerl"},{"id":"2409.14674","title":"RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning","created":"2024-09-23","cited_by_count":49,"area":"offlinerl"},{"id":"2409.01369","title":"Imitating Language via Scalable Inverse Reinforcement Learning","created":"2024-09-02","cited_by_count":21,"area":"offlinerl"},{"id":"2402.02429","title":"Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning","created":"2024-02-04","cited_by_count":17,"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":"2402.03081","title":"Preference-Conditioned Language-Guided Abstraction","created":"2024-02-05","cited_by_count":12,"area":"offlinerl"},{"id":"2406.05064","title":"Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning","created":"2024-06-07","cited_by_count":10,"area":"offlinerl"},{"id":"2409.14491","title":"Work Smarter Not Harder: Simple Imitation Learning with CS-PIBT Outperforms Large Scale Imitation Learning for MAPF","created":"2024-09-22","cited_by_count":10,"area":"offlinerl"},{"id":"2410.22269","title":"Fourier Head: Helping Large Language Models Learn Complex Probability Distributions","created":"2024-10-29","cited_by_count":10,"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":"2504.15046","title":"Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision","created":"2025-04-21","cited_by_count":5,"area":"offlinerl"},{"id":"2409.06985","title":"Unveiling Markov Heads in Pretrained Language Models for Offline Reinforcement Learning","created":"2024-09-11","cited_by_count":3,"area":"offlinerl"},{"id":"2203.16464","title":"Towards Interpretable Deep Reinforcement Learning Models via Inverse Reinforcement Learning","created":"2022-03-30","cited_by_count":2,"area":"offlinerl"},{"id":"2504.21769","title":"LLM-based Interactive Imitation Learning for Robotic Manipulation","created":"2025-04-30","cited_by_count":2,"area":"offlinerl"},{"id":"2404.09717","title":"Unveiling Imitation Learning: Exploring the Impact of Data Falsity to Large Language Model","created":"2024-04-15","cited_by_count":1,"area":"offlinerl"},{"id":"2404.10393","title":"Offline Trajectory Optimization for Offline Reinforcement Learning","created":"2024-04-16","cited_by_count":1,"area":"offlinerl"},{"id":"2410.12238","title":"Off-dynamics Conditional Diffusion Planners","created":"2024-10-16","cited_by_count":0,"area":"offlinerl"},{"id":"2411.05340","title":"Improving Multi-Domain Task-Oriented Dialogue System with Offline Reinforcement Learning","created":"2024-11-08","cited_by_count":0,"area":"offlinerl"},{"id":"2603.03960","title":"Structural Action Transformer for 3D Dexterous Manipulation","created":"2026-03-04","cited_by_count":0,"area":"offlinerl"},{"id":"2609.35375","title":"From Pixel to Poses: Object-centric Tool Manipulation Learning from Human Demonstrations","created":"2026-09-28","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}