状態非依存の方策を用いた新しい強化学習手法の提案

DOI Web Site 参考文献1件

書誌事項

タイトル別名
  • <b>Proposal of New Reinforcement Learning with a State-independent Policy</b>
  • ジョウタイ ヒイソン ノ ホウサク オ モチイタ アタラシイ キョウカ ガクシュウ シュホウ ノ テイアン
  • Proposal of New Reinforcement Learning with a State-independent Policy

この論文をさがす

抄録

Usually, reinforcement learning (RL) algorithms have a difficulty to learn the optimal control policy as the dimensionality of the state (and action) becomes large, because of the explosive increase in the search space to optimize. To avoid such an unfavorable explosive increase, in this study, we propose BASLEM algorithm (Blind Action Sequence Learning with EM algorithm) which acquires a state-independent and time-dependent control policy starting from a certain fixed initial state. Numerical simulation to control a non-holonomic system shows that RL of state-independent and time-dependent policies attain great improvement in efficiency over the existing RL algorithm.

収録刊行物

参考文献 (1)*注記

もっと見る

関連プロジェクト

もっと見る

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ