{"total":15,"rows":[{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546,"area":"offlinerl"},{"id":"2601.19897","title":"Self-Distillation Enables Continual Learning","created":"2026-01-27","cited_by_count":247,"area":"offlinerl"},{"id":"2206.11871","title":"Offline RL for Natural Language Generation with Implicit Language Q Learning","created":"2022-06-05","cited_by_count":138,"area":"offlinerl"},{"id":"2010.05848","title":"Human-centric Dialog Training via Offline Reinforcement Learning","created":"2020-10-12","cited_by_count":93,"area":"offlinerl"},{"id":"2402.07876","title":"Policy Improvement using Language Feedback Models","created":"2024-02-12","cited_by_count":16,"area":"offlinerl"},{"id":"2402.03081","title":"Preference-Conditioned Language-Guided Abstraction","created":"2024-02-05","cited_by_count":12,"area":"offlinerl"},{"id":"2306.09526","title":"Residual Q-Learning: Offline and Online Policy Customization without Value","created":"2023-06-15","cited_by_count":10,"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":"2512.16911","title":"Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning","created":"2025-12-18","cited_by_count":8,"area":"offlinerl"},{"id":"2407.00898","title":"Residual-MPPI: Online Policy Customization for Continuous Control","created":"2024-07-01","cited_by_count":7,"area":"offlinerl"},{"id":"2503.11019","title":"Residual Policy Gradient: A Reward View of KL-regularized Objective","created":"2025-03-14","cited_by_count":2,"area":"offlinerl"},{"id":"2410.05715","title":"Demonstration Based Explainable AI for Learning from Demonstration Methods","created":"2024-10-08","cited_by_count":1,"area":"offlinerl"},{"id":"2602.14844","title":"Interactionless Inverse Reinforcement Learning: A Data-Centric Framework for Durable Alignment","created":"2026-02-16","cited_by_count":1,"area":"offlinerl"},{"id":"2604.13175","title":"Pareto-Optimal Offline Reinforcement Learning via Smooth Tchebycheff Scalarization","created":"2026-04-14","cited_by_count":0,"area":"offlinerl"},{"id":"2605.30903","title":"Inverse Reinforcement Learning without an Optimal Demonstrator: A Feasible Reward Set Approach","created":"2026-05-29","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}