arXiv AI
Refinement-based Flow Policy Optimization
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 15
A Survey of Flow Matching in Reinforcement Learning
arXiv:2610.16275v1 Announce Type: cross Abstract: Flow Matching (FM) has recently emerged as a principled and efficient generative modeling framework for reinforcement learning (RL), enabling express...
arXiv Machine Learning
Oct 22
Value-Rectified Distillation for Flow-based Offline Reinforcement Learning
arXiv:2610.29075v1 Announce Type: new Abstract: We aim to address the problem of Out-of-Distribution (OOD) Mode Averaging, a critical problem that emerges when distilling Flow Matching (FM) based beh...
arXiv AI
Sep 15
Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport
arXiv:2609.15883v1 Announce Type: cross Abstract: Offline reinforcement learning aims to learn a policy solely from fixed datasets, which often contain multimodal action distributions. Flow policies...
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.
arXiv AI
Jun 30
Dual-Flow Reinforcement Learning with State-Aware Exploration
arXiv:2606. 29820v1 Announce Type: cross Abstract: In complex continuous-control reinforcement learning tasks, multimodal optimal actions often coincide with uncertain, multimodal return distributions, making reliable value estimation and multimodal exploration challenging.
arXiv AI
Oct 19
Sample-Efficient Reinforcement Learning for Policy Improvement via Flow-Reversed Action Anchors
The paper introduces AnchorQ, a method that improves sample-efficient reinforcement learning for policy refinement by using flow-reversed action anchors. AnchorQ maps reference behaviors to state-conditioned latent anchors, samples local particles around these anchors, and employs value-guided sampling to explore promising refinements. Experiments on simulated and real-world manipulation tasks show that AnchorQ outperforms state-of-the-art post-training baselines, achieving a 37% higher real-world success rate and 97% greater simulated task throughput within the same interaction budget.