Multi-dimensional reinforcement learning using a vector Q-net - Application to mobile robots

Kazuo Kiguchi, Thrishantha Nanayakkara, Keigo Watanabe, Toshio Fukuda

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)

Abstract

Reinforcement learning is considered as an important tool for robotic learning in unknown/uncertain environments. In this paper, we propose an evaluation function expressed in a vector form to realize multi-dimensional reinforcement learning. The novel feature of the proposed method is that learning one behavior induces parallel learning of other behaviors though the objectives of each behavior are different. In brief, all behaviors watch other behaviors from a critical point of view. Therefore, in the proposed method, there is cross-criticism and parallel learning that make the multi-dimensional learning process more efficient. By applying the proposed learning method, we carried out multi-dimensional evaluation (reward) and multi-dimensional learning simultaneously in one trial. A special neural network (Q-net), in which the weights and the output are represented by vectors, is proposed to realize a critic network for Q-learning. The proposed learning method is applied for behavior planning of mobile robots.

Original languageEnglish
Pages (from-to)142-148
Number of pages7
JournalInternational Journal of Control, Automation and Systems
Volume1
Issue number1
Publication statusPublished - Jan 1 2003
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Multi-dimensional reinforcement learning using a vector Q-net - Application to mobile robots'. Together they form a unique fingerprint.

Cite this