文献
J-GLOBAL ID:201702237960093152
整理番号:17A1271548
初期化の不要な誘導政策探索:確率的初期状態を用いた効率的な深部強化学習【Powered by NICT】
Reset-free guided policy search: Efficient deep reinforcement learning with stochastic initial states
著者 (5件):
Montgomery William
(Department of Computer Science and Engineering, University of Washington, Seattle, WA 98195)
,
Ajay Anurag
(Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, Berkeley, CA 94709)
,
Finn Chelsea
(Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, Berkeley, CA 94709)
,
Abbeel Pieter
(Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, Berkeley, CA 94709)
,
Levine Sergey
(Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, Berkeley, CA 94709)
資料名:
IEEE Conference Proceedings
(IEEE Conference Proceedings)
巻:
2017
号:
ICRA
ページ:
3373-3380
発行年:
2017年
JST資料番号:
W2441A
資料種別:
会議録 (C)
記事区分:
原著論文
発行国:
アメリカ合衆国 (USA)
言語:
英語 (EN)