Offline Multitask Representation Learning for Reinforcement Learning

We study offline multitask representation learning in reinforcement learning (RL), where a learner is provided with an offline dataset from different tasks that share a common representation and is asked to learn the shared representation. We theoretically investigate offline multitask low-rank RL,...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-10
Main Authors: Haque Ishfaq, Nguyen-Tang, Thanh, Feng, Songtao, Arora, Raman, Wang, Mengdi, Yin, Ming, Precup, Doina
Format: Article
Language:English
Subjects:
Algorithms
Representations
Upstream
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We study offline multitask representation learning in reinforcement learning (RL), where a learner is provided with an offline dataset from different tasks that share a common representation and is asked to learn the shared representation. We theoretically investigate offline multitask low-rank RL, and propose a new algorithm called MORL for offline multitask representation learning. Furthermore, we examine downstream RL in reward-free, offline and online scenarios, where a new task is introduced to the agent that shares the same representation as the upstream offline tasks. Our theoretical results demonstrate the benefits of using the learned representation from the upstream offline task instead of directly learning the representation of the low-rank model.
ISSN:2331-8422