{"total":16,"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":"2310.05905","title":"TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models","created":"2023-10-09","cited_by_count":53,"area":"offlinerl"},{"id":"2310.20587","title":"Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning","created":"2023-10-31","cited_by_count":24,"area":"offlinerl"},{"id":"2406.09738","title":"Contrastive Imitation Learning for Language-guided Multi-Task Robotic Manipulation","created":"2024-06-14","cited_by_count":15,"area":"offlinerl"},{"id":"2506.13762","title":"Touch begins where vision ends: Generalizable policies for contact-rich manipulation","created":"2025-06-16","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":"2604.14265","title":"Reinforcement Learning via Value Gradient Flow","created":"2026-04-15","cited_by_count":5,"area":"offlinerl"},{"id":"2312.17479","title":"Culturally-Attuned Moral Machines: Implicit Learning of Human Value Systems by AI through Inverse Reinforcement Learning","created":"2023-12-29","cited_by_count":3,"area":"offlinerl"},{"id":"2505.20335","title":"Language Model Distillation: A Temporal Difference Imitation Learning Perspective","created":"2025-05-24","cited_by_count":2,"area":"offlinerl"},{"id":"2508.01167","title":"T2S: Tokenized Skill Scaling for Lifelong Imitation Learning","created":"2025-08-02","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":"2408.07986","title":"Experimental evaluation of offline reinforcement learning for HVAC control in buildings","created":"2024-08-15","cited_by_count":0,"area":"offlinerl"},{"id":"2410.11276","title":"ILAEDA: An Imitation Learning Based Approach for Automatic Exploratory Data Analysis","created":"2024-10-15","cited_by_count":0,"area":"offlinerl"},{"id":"2509.13934","title":"Large Language Model-Empowered Decision Transformer for UAV-Enabled Data Collection","created":"2025-09-17","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":"2608.20208","title":"RoMAN-Flow: Taming Autoregressive Normalizing Flows for Offline Reinforcement Learning in Robotic Manipulation","created":"2026-08-20","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}