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

Junichi Murata, Masafumi Suzuki, Kotaro Hirasawa

Research output: Contribution to conferencePaperpeer-review

2 Citations (Scopus)


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


Other2002 International Joint Conference on Neural Networks (IJCNN '02)
Country/TerritoryUnited States
CityHonolulu, HI

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this