Weighted likelihood policy search with model selection

Tsuyoshi Ueno, Kohei Hayashi, Takashi Washio, Yoshinobu Kawahara

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

2 被引用数 (Scopus)

抄録

Reinforcement learning (RL) methods based on direct policy search (DPS) have been actively discussed to achieve an efficient approach to complicated Markov decision processes (MDPs). Although they have brought much progress in prac- tical applications of RL, there still remains an unsolved problem in DPS related to model selection for the policy. In this paper, we propose a novel DPS method, weighted likelihood policy search (WLPS), where a policy is efficiently learned through the weighted likelihood estimation. WLPS naturally connects DPS to the statistical inference problem and thus various sophisticated techniques in statis- tics can be applied to DPS problems directly. Hence, by following the idea of the information criterion, we develop a new measurement for model comparison in DPS based on the weighted log-likelihood.

本文言語英語
ホスト出版物のタイトルAdvances in Neural Information Processing Systems 25
ホスト出版物のサブタイトル26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012
ページ2357-2365
ページ数9
出版ステータス出版済み - 2012
外部発表はい
イベント26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012 - Lake Tahoe, NV, 米国
継続期間: 12 3 201212 6 2012

出版物シリーズ

名前Advances in Neural Information Processing Systems
3
ISSN(印刷版)1049-5258

会議

会議26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012
Country米国
CityLake Tahoe, NV
Period12/3/1212/6/12

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

フィンガープリント 「Weighted likelihood policy search with model selection」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル