Title:
情報処理装置、情報処理方法、およびプログラム
Document Type and Number:
Japanese Patent JP7242508
Kind Code:
B2
Abstract:
An information processing device includes a definer, a determiner, and a reinforcement learner. The definer is configured to associate a node and an edge with attributes and to define a convolution function associated with a model representing data of a graph structure representing a system structure on the basis of data regarding the graph structure. The evaluator is configured to input a state of the system into the model. The evaluator is configured to obtain, for each time step, a policy function as a probability distribution of a structural change and a state value function for reinforcement learning for a system of one or more structurally changed models which have been changed with assumable structural changes from the model for each time step. The evaluator is configured to evaluate the structural changes in the system on the basis of the policy function. The reinforcement learner is configured to perform reinforcement learning by using a reward value as a cost generated when the structural change is applied to the system, the state value function, and the model, to optimize the structural change in the system.
Inventors:
Yukio Kamagaya
Hidemasa Ito
Katsuyuki Hanai
Mayumi Yuasa
Su Mingkabura
Hidemasa Ito
Katsuyuki Hanai
Mayumi Yuasa
Su Mingkabura
Application Number:
JP2019196584A
Publication Date:
March 20, 2023
Filing Date:
October 29, 2019
Export Citation:
Assignee:
Toshiba Corporation
Toshiba Digital Solutions Corporation
Toshiba Digital Solutions Corporation
International Classes:
G06N20/00; G06V10/764
Domestic Patent References:
| JP201956960A | ||||
| JP201932659A | ||||
| JP2020178403A |
Foreign References:
| US20170061276 | ||||
| US20080077368 |
Other References:
伊藤 秀将 ほか,グラフ構造深層強化学習による電力系統制御,FIT2019 第18回情報科学技術フォーラム 講演論文集 第2分冊,日本,一般社団法人 情報処理学会,2019年08月20日,F-012,p.277-281
Attorney, Agent or Firm:
Patent Attorney Shiga International Patent Office