arXiv AI June 2, 2026 By Perry Dong, Chongyi Zheng, Chelsea Finn, Dorsa Sadigh, Benjamin Eysenbach

Value Flows

arXiv:2510. 07650v4 Announce Type: replace-cross Abstract: While most reinforcement learning methods today flatten the distribution of future returns to a single scalar value, distributional RL methods exploit the return distribution to provide stronger learning signals and to enable applications in exploration and safe RL.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 5

Path-Coupled Bellman Flows for Distributional Reinforcement Learning

arXiv:2605. 08253v2 Announce Type: replace Abstract: Distributional reinforcement learning (DRL) models the full return distribution, but existing finite-support or quantile-based methods rely on projections, while recent flow-based approaches can suffer from \emph{boundary mismatch} at the flow source or from \emph{high-variance} bootstrapping when current and successor noises are independent.

By Boyang Xu, Qing Zou, Siqin Yang, Hao Yan

diffusion reinforcement-learning safety

arXiv AI

Jun 17

Reversal Q-Learning

arXiv:2606. 17551v1 Announce Type: cross Abstract: Iterative generative modeling techniques, such as flow matching, provide powerful tools to model complex behaviors for effective offline reinforcement learning (RL).

By Aditya Oberai, Seohong Park, Sergey Levine

diffusion reinforcement-learning robotics benchmarks safety

arXiv AI

Sep 15

Refinement-based Flow Policy Optimization

arXiv:2609.15123v1 Announce Type: cross Abstract: Flow-based policies offer an expressive representation for online reinforcement learning, but conventional flow matching requires samples drawn from...

By Bumgeun Park, Hyukjun Yang, Donghwan Lee

diffusion reinforcement-learning multimodal

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

Jun 15

PERRY: Policy Evaluation with Confidence Intervals using Auxiliary Data

arXiv:2507. 20068v2 Announce Type: replace Abstract: Off-policy evaluation (OPE) methods estimate the value of a new reinforcement learning (RL) policy prior to deployment.

By Aishwarya Mandyam, Jason Meng, Ge Gao, Jiankai Sun, Mac Schwager, Barbara E. Engelhardt, Emma Brunskill

reinforcement-learning robotics

arXiv Machine Learning

Jul 30

Collaborative Weighting with Pessimistic Critic for Mitigating Overestimation in Off-Policy Reinforcement Learning

arXiv:2607. 26509v1 Announce Type: new Abstract: Deep off-policy reinforcement learning algorithms for continuous control typically rely on neural value function approximation to guide policy improvement.

By Gong Gao, Xiao Lai, Ziqi Xie, Guojie Chen, Xianhui Liu, Weidong Zhao

reinforcement-learning safety

One email a morning, machine-written

Related stories

Path-Coupled Bellman Flows for Distributional Reinforcement Learning

Reversal Q-Learning

Refinement-based Flow Policy Optimization

Robust Regularized Policy Iteration under Transition Uncertainty

PERRY: Policy Evaluation with Confidence Intervals using Auxiliary Data

Collaborative Weighting with Pessimistic Critic for Mitigating Overestimation in Off-Policy Reinforcement Learning