Prediction based segmentation of state space and application to a subgoal finding problem in reinforcement learning

被引：0

作者：

Nagata, Y ^{[1
]}

Ohigashi, Y ^{[1
]}

Takahashi, H ^{[1
]}

Ishikawa, S ^{[1
]}

Omori, T ^{[1
]}

Morikawa, K ^{[1
]}

机构：

[1] Hokkaido Univ, Grad Sch Informat Sci, Sapporo, Hokkaido, Japan

来源：

SICE 2004 ANNUAL CONFERENCE, VOLS 1-3 | 2004年

关键词：

segmentation; reinforcement learning; subgoal; acceleration of learning;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Humans solve problems by segmenting perceived continuous phenomenon and searching for action in compressed problem space. In this paper, we propose a method for segmenting continuous state space based on local prediction and a long-term prediction of continuous phenomenon. Furthermore, we investigate a subgoal finding problem in reinforcement learning as an instance of application of the segmentation result. A state having a subgoal function is found by propagating value from goal in a compressed state space. Reinforcement learning is accelerated by establishing subrewards in the state.

引用

页码：2560 / 2565

页数：6