R‐learning with multiple state‐action value tables |
| |
| Authors: | Koichiro Ishikawa Akito Sakurai Tsutomu Fujinami Susumu Kunifuji |
| |
| Affiliation: | 1. Japan Advanced Institute of Science and Technology, Japan;2. Keio University, Japan |
| |
| Abstract: | We propose a method to improve the performance of R‐learning, a reinforcement learning algorithm, by using multiple state‐action value tables. Unlike Q‐ or Sarsa learning, R‐learning learns a policy to maximize undiscounted rewards. Multiple state‐action value tables cause substantial explorations as needed and make R‐learning work well. Efficiency of the proposed method is verified through experiments in a simulated environment. © 2007 Wiley Periodicals, Inc. Electr Eng Jpn, 159(3): 34– 47, 2007; Published online in Wiley InterScience ( www.interscience. wiley.com ). DOI 10.1002/eej.20473 |
| |
| Keywords: | reinforcement learning R‐learning autonomous mobile robot |
|
|
