Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kim, Junsu, Park, Seohong, Levine, Sergey
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2408.14785
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929475652943872
author Kim, Junsu
Park, Seohong
Levine, Sergey
author_facet Kim, Junsu
Park, Seohong
Levine, Sergey
contents Offline-to-online reinforcement learning (RL), a framework that trains a policy with offline RL and then further fine-tunes it with online RL, has been considered a promising recipe for data-driven decision-making. While sensible, this framework has drawbacks: it requires domain-specific offline RL pre-training for each task, and is often brittle in practice. In this work, we propose unsupervised-to-online RL (U2O RL), which replaces domain-specific supervised offline RL with unsupervised offline RL, as a better alternative to offline-to-online RL. U2O RL not only enables reusing a single pre-trained model for multiple downstream tasks, but also learns better representations, which often result in even better performance and stability than supervised offline-to-online RL. To instantiate U2O RL in practice, we propose a general recipe for U2O RL to bridge task-agnostic unsupervised offline skill-based policy pre-training and supervised online fine-tuning. Throughout our experiments in nine state-based and pixel-based environments, we empirically demonstrate that U2O RL achieves strong performance that matches or even outperforms previous offline-to-online RL approaches, while being able to reuse a single pre-trained model for a number of different downstream tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2408_14785
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Unsupervised-to-Online Reinforcement Learning
Kim, Junsu
Park, Seohong
Levine, Sergey
Machine Learning
Offline-to-online reinforcement learning (RL), a framework that trains a policy with offline RL and then further fine-tunes it with online RL, has been considered a promising recipe for data-driven decision-making. While sensible, this framework has drawbacks: it requires domain-specific offline RL pre-training for each task, and is often brittle in practice. In this work, we propose unsupervised-to-online RL (U2O RL), which replaces domain-specific supervised offline RL with unsupervised offline RL, as a better alternative to offline-to-online RL. U2O RL not only enables reusing a single pre-trained model for multiple downstream tasks, but also learns better representations, which often result in even better performance and stability than supervised offline-to-online RL. To instantiate U2O RL in practice, we propose a general recipe for U2O RL to bridge task-agnostic unsupervised offline skill-based policy pre-training and supervised online fine-tuning. Throughout our experiments in nine state-based and pixel-based environments, we empirically demonstrate that U2O RL achieves strong performance that matches or even outperforms previous offline-to-online RL approaches, while being able to reuse a single pre-trained model for a number of different downstream tasks.
title Unsupervised-to-Online Reinforcement Learning
topic Machine Learning
url https://arxiv.org/abs/2408.14785