Switching Reinforcement Learning for Continuous Action Space

Nagayoshi Masato, Murao Hajime, Tamaki Hisashi

doi:10.1541/ieejeiss.131.976

Bibliographic Information

Other Title

連続行動空間への適用を考慮したSwitching強化学習
レンゾクコウドウクウカンエノテキヨウオコウリョシタ Switching キョウカガクシュウ

Search this article

Abstract

Reinforcement Learning (RL) attracts much attention as a technique of realizing computational intelligence such as adaptive and autonomous decentralized systems. In general, however, it is not easy to put RL into practical use. This difficulty includes a problem of designing a suitable action space of an agent, i.e., satisfying two requirements in trade-off: (i) to keep the characteristics (or structure) of an original search space as much as possible in order to seek strategies that lie close to the optimal, and (ii) to reduce the search space as much as possible in order to expedite the learning process.<br>In order to design a suitable action space adaptively, we propose switching RL model to mimic a process of an infant's motor development in which gross motor skills develop before fine motor skills. Then, a method for switching controllers is constructed by introducing and referring to the “entropy”. Further, through computational experiments by using robot navigation problems with one and two-dimensional continuous action space, the validity of the proposed method has been confirmed.

Journal

IEEJ Transactions on Electronics, Information and Systems

IEEJ Transactions on Electronics, Information and Systems 131 (5), 976-982, 2011

The Institute of Electrical Engineers of Japan

Keywords

Details 詳細情報について

Export