Networks with input gates for situation-dependent input selection in reinforcement learning

Junichi Murata, Masafumi Suzuki, Kotaro Hirasawa

Research output: Contribution to conferencePaper

2 Citations (Scopus)

Abstract

A method is proposed for situation-dependent input selection and learning acceleration in Q-learning. Q-values are expressed by an RBF network which has an input gate attached to each of its input channels in order to capture, by learning, situation-dependent relevance or usefulness of the input.

Original languageEnglish
Pages5-10
Number of pages6
Publication statusPublished - Jan 1 2002
Event2002 International Joint Conference on Neural Networks (IJCNN '02) - Honolulu, HI, United States
Duration: May 12 2002May 17 2002

Other

Other2002 International Joint Conference on Neural Networks (IJCNN '02)
CountryUnited States
CityHonolulu, HI
Period5/12/025/17/02

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

Murata, J., Suzuki, M., & Hirasawa, K. (2002). Networks with input gates for situation-dependent input selection in reinforcement learning. 5-10. Paper presented at 2002 International Joint Conference on Neural Networks (IJCNN '02), Honolulu, HI, United States.