Efficient and Uncertainty-Aware Diffusion Framework for Offline-to-Online Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bui, Ha Manh, Jazbec, Metod, Nalisnick, Eric, Liu, Anqi
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918531193372672
author Bui, Ha Manh
Jazbec, Metod
Nalisnick, Eric
Liu, Anqi
author_facet Bui, Ha Manh
Jazbec, Metod
Nalisnick, Eric
Liu, Anqi
contents Offline-to-Online Reinforcement Learning (O2O-RL) leverages an offline, pre-trained policy to minimize costly online interactions. Although data-efficient, O2O-RL is susceptible to shifts between offline and online distributions. Existing work aims to mitigate the harm of this shift by finetuning the policy on trajectory data sampled from a diffusion model. Inspired by this line of work, we propose DUAL: an efficient \textbf{D}iffusion \textbf{U}ncertainty-\textbf{A}ware framework for offline-to-online reinforcement \textbf{L}earning. DUAL utilizes the prior knowledge of the diffusion model to distill a fast-sampling diffusion actor policy and transition model in the offline phase. DUAL also employs a Laplace approximation and distance transition-state-shift detection, thereby using uncertainty quantification to improve exploration versus exploitation in the online phase. We formally show that our actor loss with the Laplace approximation provides a proxy for a principled estimate of epistemic uncertainty. Empirically, DUAL improves the online expected return over O2O-RL baselines across multiple settings and environments.
format Preprint
id arxiv_https___arxiv_org_abs_2605_30776
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Efficient and Uncertainty-Aware Diffusion Framework for Offline-to-Online Reinforcement Learning
Bui, Ha Manh
Jazbec, Metod
Nalisnick, Eric
Liu, Anqi
Machine Learning
Offline-to-Online Reinforcement Learning (O2O-RL) leverages an offline, pre-trained policy to minimize costly online interactions. Although data-efficient, O2O-RL is susceptible to shifts between offline and online distributions. Existing work aims to mitigate the harm of this shift by finetuning the policy on trajectory data sampled from a diffusion model. Inspired by this line of work, we propose DUAL: an efficient \textbf{D}iffusion \textbf{U}ncertainty-\textbf{A}ware framework for offline-to-online reinforcement \textbf{L}earning. DUAL utilizes the prior knowledge of the diffusion model to distill a fast-sampling diffusion actor policy and transition model in the offline phase. DUAL also employs a Laplace approximation and distance transition-state-shift detection, thereby using uncertainty quantification to improve exploration versus exploitation in the online phase. We formally show that our actor loss with the Laplace approximation provides a proxy for a principled estimate of epistemic uncertainty. Empirically, DUAL improves the online expected return over O2O-RL baselines across multiple settings and environments.
title Efficient and Uncertainty-Aware Diffusion Framework for Offline-to-Online Reinforcement Learning
topic Machine Learning
url https://arxiv.org/abs/2605.30776