{"total":20,"rows":[{"id":"2410.04640","title":"Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progress","created":"2024-10-06","cited_by_count":69,"area":"offlinerl"},{"id":"2506.04168","title":"Horizon Reduction Makes RL Scalable","created":"2025-06-04","cited_by_count":57,"area":"offlinerl"},{"id":"2412.01441","title":"LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations","created":"2024-12-02","cited_by_count":32,"area":"offlinerl"},{"id":"2306.00323","title":"Thought Cloning: Learning to Think while Acting by Imitating Human Thinking","created":"2023-06-01","cited_by_count":30,"area":"offlinerl"},{"id":"2505.22866","title":"Scaling Offline RL via Efficient and Expressive Shortcut Models","created":"2025-05-28","cited_by_count":27,"area":"offlinerl"},{"id":"2410.23254","title":"Keypoint Abstraction using Large Models for Object-Relative Imitation Learning","created":"2024-10-30","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":"2311.00267","title":"Rethinking Decision Transformer via Hierarchical Reinforcement Learning","created":"2023-11-01","cited_by_count":14,"area":"offlinerl"},{"id":"2408.10504","title":"QPO: Query-dependent Prompt Optimization via Multi-Loop Offline Reinforcement Learning","created":"2024-08-20","cited_by_count":10,"area":"offlinerl"},{"id":"2505.03209","title":"DYSTIL: Dynamic Strategy Induction with Large Language Models for Reinforcement Learning","created":"2025-05-06","cited_by_count":7,"area":"offlinerl"},{"id":"2411.15131","title":"WildLMa: Long Horizon Loco-Manipulation in the Wild","created":"2024-11-22","cited_by_count":6,"area":"offlinerl"},{"id":"2602.03389","title":"Chain-of-Goals Hierarchical Policy for Long-Horizon Offline Goal-Conditioned RL","created":"2026-02-03","cited_by_count":5,"area":"offlinerl"},{"id":"2509.22023","title":"Teaching Transformers to Solve Combinatorial Problems through Efficient Trial & Error","created":"2025-09-26","cited_by_count":3,"area":"offlinerl"},{"id":"2501.16546","title":"Sample-Efficient Behavior Cloning Using General Domain Knowledge","created":"2025-01-27","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":"2310.13004","title":"Progressively Efficient Learning","created":"2023-10-13","cited_by_count":1,"area":"offlinerl"},{"id":"2410.02231","title":"SEAL: SEmantic-Augmented Imitation Learning via Language Model","created":"2024-10-03","cited_by_count":1,"area":"offlinerl"},{"id":"2509.05368","title":"Long-Horizon Visual Imitation Learning via Plan and Code Reflection","created":"2025-09-04","cited_by_count":1,"area":"offlinerl"},{"id":"2603.24883","title":"Learning to Staff: Offline Reinforcement Learning and Fine-Tuned LLMs for Warehouse Staffing Optimization","created":"2026-03-25","cited_by_count":0,"area":"offlinerl"},{"id":"2609.35880","title":"From Static Policies to Adaptive Priors in Offline Reinforcement Learning","created":"2026-09-26","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}