1A1-F10 異種センサ統合のためのニューラルネットワーク型強化学習(進化・学習とロボティクス(1))

書誌事項

タイトル別名
  • 1A1-F10 Neural Network Reinforcement Learning for Different-Species Sensor Integration(Evolution and Learning for Robotics(1))

抄録

This paper proposes a new reinforcement learning algorithm which can learn in the multi-dimensional input spaces containing different-species sensors by means of CMAC and neural networks. We apply the proposed method to a robot arm reaching problem and verify the effectivity of the proposed method.

収録刊行物

詳細情報 詳細情報について

問題の指摘

ページトップへ