Offline Multitask Representation Learning for Reinforcement Learning

Haque Ishfaq, Thanh Nguyen-Tang, Songtao Feng, Raman Arora, Mengdi Wang, Ming Yin, Doina Precup

Keywords: Multitask learning, representation Learning, offline RL, provably efficient, suboptimality gap, reward-free RL

TL;DR: We show provable benefit of offline multitask reinforcement learning for both upstream and downstream tasks when certain part of representation is shared among the tasks.

Abstract: 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.

Primary Area: Reinforcement learning

Submission Number: 8601