arXiv Machine Learning June 24, 2026 By Qihao Ye, Xiaochuan Tian, Yuhua Zhu

A Robust Model-Based Approach for Continuous-Time Policy Evaluation with Unknown L\'evy Process Dynamics

Read the original on arXiv Machine Learning →

arXiv:2504. 01482v3 Announce Type: replace-cross Abstract: This paper develops a model-based framework for continuous-time policy evaluation (CTPE) in reinforcement learning, incorporating both Brownian and L\'evy noise to model stochastic dynamics influenced by rare and extreme events.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

reinforcement-learning

arXiv AI

Jun 18

Robust Regularized Policy Iteration under Transition Uncertainty

arXiv:2603. 09344v3 Announce Type: replace Abstract: Offline reinforcement learning (RL) enables data-efficient and safe policy learning without online exploration, but its performance often degrades under distribution shift.

By Hongqiang Lin, Zhenghui Fu, Weihao Tang, Pengfei Wang, Yiding Sun, Qixian Huang, Dongxu Zhang

reinforcement-learning benchmarks

arXiv Machine Learning

Jul 28

Online Policy Evaluation for MDPs with Dynamic UBSR Measures

arXiv:2607. 23030v1 Announce Type: new Abstract: Developing efficient function-approximation methods for policy evaluation is a fundamental challenge in risk-aware reinforcement learning.

By Weikai Wang, Erick Delage

reinforcement-learning

arXiv Machine Learning

Jul 27

Generalized Gaussian Temporal Difference Error for Uncertainty-aware Reinforcement Learning

arXiv:2408. 02295v4 Announce Type: replace Abstract: Conventional uncertainty-aware temporal difference (TD) learning often models TD errors as zero-mean Gaussian.

By Seyeon Kim, Joonhun Lee, Namhoon Cho, Sungjun Han, Wooseop Hwang

reinforcement-learning benchmarks

arXiv AI

Jun 17

Kolmogorov Regression for Robust Diffusion Policies

arXiv:2606. 18186v1 Announce Type: cross Abstract: Finite-dimensional (FD) diffusion policies exhibit temporal drift owing to discretization artifacts that degrade long-horizon performance (when deployed on physical systems).

By Lekan Molu

diffusion robotics benchmarks

arXiv Machine Learning

Jun 19

Off-Policy Evaluation for Missingness-Aware Policies in MDPs with Rewards Missing Not at Random

arXiv:2606. 20206v1 Announce Type: cross Abstract: In offline Reinforcement Learning, immediate rewards in logged batch data are often unobserved due to sparse or irregular record-keeping, or censored beyond certain reward values.

By Ziheng Wei, Annie Qu, Rui Miao

reinforcement-learning safety

arXiv Machine Learning

Jul 17

A Continuous-Time Reinforcement Learning Framework for Fine-Tuning Discrete Diffusion Models

arXiv:2607. 14522v1 Announce Type: new Abstract: We formulate reinforcement learning (RL) in continuous time with discrete state spaces and possibly arbitrary action spaces via a stochastic control approach, where the state dynamics are modeled as a controlled continuous-time Markov chain (CTMC).

By Zikun Zhang, Jiayuan Sheng, David D. Yao, Wenpin Tang

llms diffusion reinforcement-learning fine-tuning

Related stories

Robust Regularized Policy Iteration under Transition Uncertainty

Online Policy Evaluation for MDPs with Dynamic UBSR Measures

Generalized Gaussian Temporal Difference Error for Uncertainty-aware Reinforcement Learning

Kolmogorov Regression for Robust Diffusion Policies

Off-Policy Evaluation for Missingness-Aware Policies in MDPs with Rewards Missing Not at Random

A Continuous-Time Reinforcement Learning Framework for Fine-Tuning Discrete Diffusion Models