paper-with-me

Papers

Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization

2022-10-07 · Jihwan Jeong, Xiaoyu Wang, Michael Gimelfarb, Hyunwoo Kim, Baher Abdulhai, Scott Sanner

Offline reinforcement learning (RL) addresses the problem of learning a performant policy from a fixed batch of data collected by following some behavior policy. Model-based approaches are particularly appealing in the offline setting since they can extract more learning signals from the logged dataset by learning a model of the environment. However, the performance of existing model-based approaches falls short of model-free counterparts, due to the compounding of estimation errors in the learned model. Driven by this observation, we argue that it is critical for a model-based method to understand when to trust the model and when to rely on model-free estimates, and how to act conservatively w.r.t. both. To this end, we derive an elegant and simple methodology called conservative Bayesian model-based value expansion for offline policy optimization (CBOP), that trades off model-free and model-based estimates during the policy evaluation step according to their epistemic uncertainties, and facilitates conservatism by taking a lower bound on the Bayesian posterior value estimate. On the standard D4RL continuous control tasks, we find that our method significantly outperforms previous model-based approaches: e.g., MOPO by $116.4$%, MOReL by $23.2$% and COMBO by $23.7$%. Further, CBOP achieves state-of-the-art performance on $11$ out of $18$ benchmark datasets while doing on par on the remaining datasets.

📄 PDF Abstract BibTeX arXiv:2210.03802

Code (1)

jihwan-jeong/cbop 공식 구현 pytorch

Tasks

continuous-controlContinuous ControlD4RLReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Bayesian Conservative Policy Optimization (BCPO): A Novel Uncertainty-Calibrated Offline Reinforcement Learning with Credible Lower Bounds

2026-03-06 · Debashis Chatterjee arxiv

Offline reinforcement learning (RL) aims to learn decision policies from a fixed batch of logged transitions, without additional environment interaction. Despite remarkable empirical progress, offline RL remains fragile …

Reinforcement LearningOffline RL

ISEP: Implicit Support Expansion for Offline Reinforcement Learning via Stochastic Policy Optimization

2026-05-18 · Yifei Chen, Shaoqin Zhu, Xiaoqiang Ji arxiv

Offline reinforcement learning methods typically enforce strict constraints to ensure safety; yet this rigidity often prevents the discovery of optimal behaviors outside the immediate support of the behavior policy. To a…

Reinforcement Learning

Peng's Q($λ$) for Conservative Value Estimation in Offline Reinforcement Learning

2026-05-14 · Byeongchan Kim, Min-hwan Oh arxiv

We propose a model-free offline multi-step reinforcement learning (RL) algorithm, Conservative Peng's Q($λ$) (CPQL). Our algorithm adapts the Peng's Q($λ$) (PQL) operator for conservative value estimation as an alternati…

Reinforcement LearningOffline RL

BiCQL-ML: A Bi-Level Conservative Q-Learning Framework for Maximum Likelihood Inverse Reinforcement Learning

2025-11-27 · Junsung Park arxiv

Offline inverse reinforcement learning (IRL) aims to recover a reward function that explains expert behavior using only fixed demonstration data, without any additional online interaction. We propose BiCQL-ML, a policy-f…

Reinforcement LearningOffline RL

Conservative State Value Estimation for Offline Reinforcement Learning

2023-02-14 · NeurIPS 2023 11 · Liting Chen, Jie Yan, Zhengdao Shao, Lu Wang 외

Offline reinforcement learning faces a significant challenge of value over-estimation due to the distributional drift between the dataset and the current learned policy, leading to learning failure in practice. The commo…

D4RLreinforcement-learningReinforcement Learning