文章基本信息

标题：A Reinforcement Learning Method Using Reward Acquisition Efficiency for POMDP Environments
本地全文：下载
作者：Hirokazu Kawai ; Atsushi Ueno ; Shoji Tatsumi 等
期刊名称：人工知能学会論文誌
印刷版ISSN：1346-0714
电子版ISSN：1346-8030
出版年度：2008
卷号：23
期号：1
页码：1-12
DOI：10.1527/tjsai.23.1
出版社：The Japanese Society for Artificial Intelligence
摘要：Reinforcement Learning (RL) methods are very hopeful because they can learn useful behavior based on rewards from environment by trial and error. This paper tackles more difficult problems than the ones tackled by many ordinary RL methods: RL in POMDP (Partially Observable Markov Decision Process) environments with multiple rewards.
关键词：reinforcement learning ; POMDPs ; reward acquisition efficiency ; multi-reward environment