Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

2-2017

Abstract

We propose a new method for transferring a policy from a source task to a target task in model-based reinforcement learning. Our work is motivated by scenarios where a robotic agent operates in similar but challenging environments, such as hospital wards, differentiated by structural arrangements or obstacles, such as furniture. We address problems that require fast responses adapted from incomplete, prior knowledge of the agent in new scenarios. We present an efficient selective exploration strategy that maximally reuses the source task policy. Reuse efficiency is effected through identifying sub-spaces that are different in the target environment, thus limiting the exploration needed in the target task. We empirically show that SEAPoT performs better in terms of jump starts and cumulative average rewards, as compared to existing state-of-the-art policy reuse methods.

Keywords

Transfer learning, policy transfer, reinforcement learning

Discipline

Numerical Analysis and Scientific Computing | Theory and Algorithms

Research Areas

Intelligent Systems and Optimization

Publication

AAAI '17: Proceedings of the 31st Conference on Artificial Intelligence, San Francisco, CA, USA, 2017 February 4-9

First Page

4975

Last Page

4976

Publisher

IFAAMAS

City or Country

Ann Arbor, MI

Copyright Owner and License

Publisher

Additional URL

https://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14729

Download

Share

COinS