{"total":13,"rows":[{"id":"2306.02707","title":"Orca: Progressive Learning from Complex Explanation Traces of GPT-4","created":"2023-06-05","cited_by_count":379,"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":"2402.07876","title":"Policy Improvement using Language Feedback Models","created":"2024-02-12","cited_by_count":16,"area":"offlinerl"},{"id":"2411.05193","title":"Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning","created":"2024-11-07","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":"2302.05507","title":"Language Decision Transformers with Exponential Tilt for Interactive Text Environments","created":"2023-02-10","cited_by_count":3,"area":"offlinerl"},{"id":"2412.00979","title":"Hierarchical Prompt Decision Transformer: Improving Few-Shot Policy Generalization with Global and Adaptive Guidance","created":"2024-12-01","cited_by_count":3,"area":"offlinerl"},{"id":"2502.10473","title":"Diverse Transformer Decoding for Offline Reinforcement Learning Using Financial Algorithmic Approaches","created":"2025-02-13","cited_by_count":0,"area":"offlinerl"},{"id":"2509.23111","title":"Liaohe-CobotMagic-PnP: an Imitation Learning Dataset of Intelligent Robot for Industrial Applications","created":"2025-09-27","cited_by_count":0,"area":"offlinerl"},{"id":"2510.11307","title":"FOSSIL: Harnessing Feedback on Suboptimal Samples for Data-Efficient Generalisation with Imitation Learning for Embodied Vision-and-Language Tasks","created":"2025-10-13","cited_by_count":0,"area":"offlinerl"},{"id":"2601.08107","title":"STO-RL: Offline RL under Sparse Rewards via LLM-Guided Subgoal Temporal Order","created":"2026-01-13","cited_by_count":0,"area":"offlinerl"},{"id":"2601.15761","title":"Off-Policy Actor-Critic with Sigmoid-Bounded Entropy for Real-World Robot Learning","created":"2026-01-22","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}