Offline Multitask Representation Learning for Reinforcement Learning
This work addresses the challenge of efficient representation learning for RL in offline settings, which is incremental as it builds on existing multitask and low-rank RL methods.
The paper tackles the problem of offline multitask representation learning in reinforcement learning by proposing the MORL algorithm, which learns a shared representation from offline datasets of different tasks and demonstrates improved performance in downstream RL scenarios.
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.