arXiv Machine Learning June 5, 2026 By Boyang Xu, Qing Zou, Siqin Yang, Hao Yan

Path-Coupled Bellman Flows for Distributional Reinforcement Learning

Read the original on arXiv Machine 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.

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

arXiv AI

Jun 2

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.

By Perry Dong, Chongyi Zheng, Chelsea Finn, Dorsa Sadigh, Benjamin Eysenbach

reinforcement-learning benchmarks

arXiv AI

Jun 9

Reinforcement Learning for Flow-Matching Policies with Density Transport

arXiv:2606. 08602v1 Announce Type: cross Abstract: We present an online reinforcement learning (RL) algorithm for fine-tuning flow-matching policies in continuous-control problems.

By Boshu Lei, Kostas Daniilidis, Antonio Loquercio

diffusion reinforcement-learning robotics fine-tuning efficiency multimodal safety

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 30

FlowAWR: Online Adaptive Flow Reinforcement via Advantage-Weighted Rectification

arXiv:2606. 30376v1 Announce Type: new Abstract: Aligning generative flow models on continuous spaces via online reinforcement learning is constrained by intractable trajectory likelihoods.

By Zheming Fu, Ruizhe He, Wei Shang, Xiaoxiao Ma, Lei Wang, Chang Liu, Siming Fu

reinforcement-learning safety

arXiv AI

Jun 16

Direction-Conditioned Policies via Compositional Subgoal Scoring for Online Goal-Conditioned Reinforcement Learning

arXiv:2606. 16515v1 Announce Type: cross Abstract: Hamilton-Jacobi-Bellman theory implies that the optimal goal-conditioned action depends on the goal only through the gradient of the goal-reaching distance at the current state, yet standard online GCRL still conditions the actor on the raw goal -- a signal that is geometrically uninformative when the goal is far from the data distribution.

By Swaminathan S K, Damiya Gondha, Theyanesh Eswaramoorthy Rajahkrishnan, Aritra Hazra

reinforcement-learning robotics

arXiv AI

Jun 11

Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions

arXiv:2509. 10303v2 Announce Type: replace-cross Abstract: Online reinforcement learning (RL) approaches have demonstrated strong performance on Job Shop Scheduling (JSP) and Flexible JSP (FJSP) problems by learning scheduling policies through direct interaction with simulated environments.

By Jesse van Remmerden, Zaharah Bukhsh, Yingqian Zhang

reinforcement-learning benchmarks

Related stories

Value Flows

Reinforcement Learning for Flow-Matching Policies with Density Transport

Robust Regularized Policy Iteration under Transition Uncertainty

FlowAWR: Online Adaptive Flow Reinforcement via Advantage-Weighted Rectification

Direction-Conditioned Policies via Compositional Subgoal Scoring for Online Goal-Conditioned Reinforcement Learning

Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions