Saved in:
Bibliographic Details
Main Authors: Tiofack, Franki Nguimatsia, Hellard, Théotime Le, Schramm, Fabian, Perrin-Gilbert, Nicolas, Carpentier, Justin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.03973
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911487702859776
author Tiofack, Franki Nguimatsia
Hellard, Théotime Le
Schramm, Fabian
Perrin-Gilbert, Nicolas
Carpentier, Justin
author_facet Tiofack, Franki Nguimatsia
Hellard, Théotime Le
Schramm, Fabian
Perrin-Gilbert, Nicolas
Carpentier, Justin
contents Offline reinforcement learning often relies on behavior regularization that enforces policies to remain close to the dataset distribution. However, such approaches fail to distinguish between high-value and low-value actions in their regularization components. We introduce Guided Flow Policy (GFP), which couples a multi-step flow-matching policy with a distilled one-step actor. The actor directs the flow policy through weighted behavior cloning to focus on cloning high-value actions from the dataset rather than indiscriminately imitating all state-action pairs. In turn, the flow policy constrains the actor to remain aligned with the dataset's best transitions while maximizing the critic. This mutual guidance enables GFP to achieve state-of-the-art performance across 144 state and pixel-based tasks from the OGBench, Minari, and D4RL benchmarks, with substantial gains on suboptimal datasets and challenging tasks. Webpage: https://simple-robotics.github.io/publications/guided-flow-policy/
format Preprint
id arxiv_https___arxiv_org_abs_2512_03973
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning
Tiofack, Franki Nguimatsia
Hellard, Théotime Le
Schramm, Fabian
Perrin-Gilbert, Nicolas
Carpentier, Justin
Machine Learning
Artificial Intelligence
Offline reinforcement learning often relies on behavior regularization that enforces policies to remain close to the dataset distribution. However, such approaches fail to distinguish between high-value and low-value actions in their regularization components. We introduce Guided Flow Policy (GFP), which couples a multi-step flow-matching policy with a distilled one-step actor. The actor directs the flow policy through weighted behavior cloning to focus on cloning high-value actions from the dataset rather than indiscriminately imitating all state-action pairs. In turn, the flow policy constrains the actor to remain aligned with the dataset's best transitions while maximizing the critic. This mutual guidance enables GFP to achieve state-of-the-art performance across 144 state and pixel-based tasks from the OGBench, Minari, and D4RL benchmarks, with substantial gains on suboptimal datasets and challenging tasks. Webpage: https://simple-robotics.github.io/publications/guided-flow-policy/
title Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2512.03973