Profit SharingとRestricted Boltzmann Machineを用いた空間の分節化による学習手法のタクシー配車計画問題へ適用

URI http://harp.lib.hiroshima-u.ac.jp/pu-hiroshima/metadata/12387
File
Title
Profit SharingとRestricted Boltzmann Machineを用いた空間の分節化による学習手法のタクシー配車計画問題へ適用
Title Alternative
A Hybrid Method of Space Segmentation by Profit Sharing and Pre-Training by Restricted Boltzmann Machine and Its Application to Taxi Allocation Planning Problem
Author
氏名 大久保 将博
ヨミ オオクボ マサヒロ
別名 Ookubo Masahiro
氏名 市村 匠
ヨミ イチムラ タクミ
別名 Ichimura Takumi
Abstract

Hierarchical Modular Reinforcement Learning (HMRL)[1] consists of 2 layered learning where Profit-Sharing works to plan a target position in the higher layer and Qlearning
trains the state-action pair to the target in the lower layer. The method can divide a complex task into subtasks, and it reduces to state dimension and improves learning capability. In order to solve this problem, we propose the learning method based on Restricted Boltzmann Machine (RBM) with subspace divided by Profit Sharing. In this paper, to verify the effectiveness of the proposed method, the assignment problem of taxies was investigated.

Description

開催日:平成28年7月16日
会場:広島大学

Journal Title
2016 IEEE SMC Hiroshima Chapter 若手研究会講演論文集
Spage
94
Epage
97
Published Date
2016
Publisher
IEEE SMC Hiroshima Chapter
Contributor
市村匠
Language
jpn
NIIType
Conference Paper
Text Version
出版社版
Set
pu-hiroshima