Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Liyu, Wu, Haochi, Wan, Xu, Kong, Quan, Deng, Ruilong, Sun, Mingyang
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2410.18626
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909503288508416
author Zhang, Liyu
Wu, Haochi
Wan, Xu
Kong, Quan
Deng, Ruilong
Sun, Mingyang
author_facet Zhang, Liyu
Wu, Haochi
Wan, Xu
Kong, Quan
Deng, Ruilong
Sun, Mingyang
contents Offline-to-online (O2O) reinforcement learning (RL) pre-trains models on offline data and refines policies through online fine-tuning. However, existing O2O RL algorithms typically require maintaining the tedious offline datasets to mitigate the effects of out-of-distribution (OOD) data, which significantly limits their efficiency in exploiting online samples. To address this deficiency, we introduce a new paradigm for O2O RL called State-Action-Conditional Offline \Model Guidance (SAMG). It freezes the pre-trained offline critic to provide compact offline understanding for each state-action sample, thus eliminating the need for retraining on offline data. The frozen offline critic is incorporated with the online target critic weighted by a state-action-adaptive coefficient. This coefficient aims to capture the offline degree of samples at the state-action level, and is updated adaptively during training. In practice, SAMG could be easily integrated with Q-function-based algorithms. Theoretical analysis shows good optimality and lower estimation error. Empirically, SAMG outperforms state-of-the-art O2O RL algorithms on the D4RL benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2410_18626
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SAMG: Offline-to-Online Reinforcement Learning via State-Action-Conditional Offline Model Guidance
Zhang, Liyu
Wu, Haochi
Wan, Xu
Kong, Quan
Deng, Ruilong
Sun, Mingyang
Machine Learning
Artificial Intelligence
Offline-to-online (O2O) reinforcement learning (RL) pre-trains models on offline data and refines policies through online fine-tuning. However, existing O2O RL algorithms typically require maintaining the tedious offline datasets to mitigate the effects of out-of-distribution (OOD) data, which significantly limits their efficiency in exploiting online samples. To address this deficiency, we introduce a new paradigm for O2O RL called State-Action-Conditional Offline \Model Guidance (SAMG). It freezes the pre-trained offline critic to provide compact offline understanding for each state-action sample, thus eliminating the need for retraining on offline data. The frozen offline critic is incorporated with the online target critic weighted by a state-action-adaptive coefficient. This coefficient aims to capture the offline degree of samples at the state-action level, and is updated adaptively during training. In practice, SAMG could be easily integrated with Q-function-based algorithms. Theoretical analysis shows good optimality and lower estimation error. Empirically, SAMG outperforms state-of-the-art O2O RL algorithms on the D4RL benchmark.
title SAMG: Offline-to-Online Reinforcement Learning via State-Action-Conditional Offline Model Guidance
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2410.18626