Timezone: »

 
Poster
Provable Benefit of Multitask Representation Learning in Reinforcement Learning
Yuan Cheng · Songtao Feng · Jing Yang · Hong Zhang · Yingbin Liang

Tue Nov 29 02:00 PM -- 04:00 PM (PST) @ Hall J #809
in Poster Session 2 »

As representation learning becomes a powerful technique to reduce sample complexity in reinforcement learning (RL) in practice, theoretical understanding of its advantage is still limited. In this paper, we theoretically characterize the benefit of representation learning under the low-rank Markov decision process (MDP) model. We first study multitask low-rank RL (as upstream training), where all tasks share a common representation, and propose a new multitask reward-free algorithm called REFUEL. REFUEL learns both the transition kernel and the near-optimal policy for each task, and outputs a well-learned representation for downstream tasks. Our result demonstrates that multitask representation learning is provably more sample-efficient than learning each task individually, as long as the total number of tasks is above a certain threshold. We then study the downstream RL in both online and offline settings, where the agent is assigned with a new task sharing the same representation as the upstream tasks. For both online and offline settings, we develop a sample-efficient algorithm, and show that it finds a near-optimal policy with the suboptimality gap bounded by the sum of the estimation error of the learned representation in upstream and a vanishing term as the number of downstream samples becomes large. Our downstream results of online and offline RL further capture the benefit of employing the learned representation from upstream as opposed to learning the representation of the low-rank model directly. To the best of our knowledge, this is the first theoretical study that characterizes the benefit of representation learning in exploration-based reward-free multitask RL for both upstream and downstream tasks.

Keywords: Representation Learning · multitask learning · offline RL · suboptimality gap.
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Yuan Cheng (University of Science and Technology of China)
Songtao Feng (Ohio State University, Columbus)
Jing Yang (Pennsylvania State University)
Hong Zhang (University of Science and Technology of China)
Yingbin Liang (The Ohio State University)

More from the Same Authors