{"total":22,"rows":[{"id":"2107.06106","title":"Conservative Offline Distributional Reinforcement Learning","created":"2021-07-12","cited_by_count":79,"area":"offlinerl"},{"id":"2212.00124","title":"One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning","created":"2022-11-30","cited_by_count":23,"area":"offlinerl"},{"id":"2402.13777","title":"Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions","created":"2024-02-21","cited_by_count":20,"area":"offlinerl"},{"id":"2301.12130","title":"Constrained Policy Optimization with Explicit Behavior Density for Offline Reinforcement Learning","created":"2023-01-28","cited_by_count":16,"area":"offlinerl"},{"id":"2206.07166","title":"Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning","created":"2022-06-14","cited_by_count":14,"area":"offlinerl"},{"id":"2202.09673","title":"A Behavior Regularized Implicit Policy for Offline Reinforcement Learning","created":"2022-02-19","cited_by_count":11,"area":"offlinerl"},{"id":"2205.10629","title":"User-Interactive Offline Reinforcement Learning","created":"2022-05-21","cited_by_count":11,"area":"offlinerl"},{"id":"2201.05433","title":"Comparing Model-free and Model-based Algorithms for Offline Reinforcement Learning","created":"2022-01-14","cited_by_count":9,"area":"offlinerl"},{"id":"2209.07288","title":"Optimistic Curiosity Exploration and Conservative Exploitation with Linear Reward Shaping","created":"2022-09-15","cited_by_count":6,"area":"offlinerl"},{"id":"2407.07631","title":"Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning","created":"2024-07-10","cited_by_count":6,"area":"offlinerl"},{"id":"2410.20312","title":"Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model","created":"2024-10-27","cited_by_count":4,"area":"offlinerl"},{"id":"2111.13461","title":"Measuring Data Quality for Dataset Selection in Offline Reinforcement Learning","created":"2021-11-26","cited_by_count":3,"area":"offlinerl"},{"id":"2403.17646","title":"Diffusion Policies for Risk-Averse Behavior Modeling in Offline Reinforcement Learning","created":"2024-03-26","cited_by_count":2,"area":"offlinerl"},{"id":"2507.03900","title":"Risk-sensitive Actor-Critic with Static Spectral Risk Measures for Online and Offline Reinforcement Learning","created":"2025-07-05","cited_by_count":2,"area":"offlinerl"},{"id":"2605.01663","title":"Towards Efficient and Expressive Offline RL via Flow-Anchored Noise-conditioned Q-Learning","created":"2026-05-03","cited_by_count":2,"area":"offlinerl"},{"id":"2605.07393","title":"Offline Policy Optimization with Posterior Sampling","created":"2026-05-08","cited_by_count":1,"area":"offlinerl"},{"id":"2606.27766","title":"RS-Diffuser: Risk-Sensitive Diffusion Planning with Distributional Value Guidance","created":"2026-06-26","cited_by_count":1,"area":"offlinerl"},{"id":"2209.13132","title":"DCE: Offline Reinforcement Learning With Double Conservative Estimates","created":"2022-09-27","cited_by_count":0,"area":"offlinerl"},{"id":"2406.07541","title":"CDSA: Conservative Denoising Score-based Algorithm for Offline Reinforcement Learning","created":"2024-06-11","cited_by_count":0,"area":"offlinerl"},{"id":"2510.02695","title":"RAMAC: Multimodal Risk-Aware Offline Reinforcement Learning and the Role of Behavior Regularization","created":"2025-10-03","cited_by_count":0,"area":"offlinerl"},{"id":"2510.03013","title":"Distributional Inverse Reinforcement Learning","created":"2025-10-03","cited_by_count":0,"area":"offlinerl"},{"id":"2606.00680","title":"Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief","created":"2026-05-30","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}