J-STAGE Home  >  Publications - Top  > Bibliographic Information

IEICE Transactions on Information and Systems
Vol. E95.D (2012) No. 10 pp. 2426-2437

Language:

http://doi.org/10.1587/transinf.E95.D.2426

Regular Section

Reinforcement learning (RL) is a flexible framework for learning a decision rule in an unknown environment. However, a large number of samples are often required for finding a useful decision rule. To mitigate this problem, the concept of transfer learning has been employed to utilize knowledge obtained from similar RL tasks. However, most approaches developed so far are useful only in low-dimensional settings. In this paper, we propose a novel transfer learning idea that targets problems with high-dimensional states. Our idea is to transfer knowledge between state factors (e.g., interacting objects) within a single RL task. This allows the agent to learn the system dynamics of the target RL task with fewer data samples. The effectiveness of the proposed method is demonstrated through experiments.

Copyright © 2012 The Institute of Electronics, Information and Communication Engineers

Article Tools

Share this Article