Invention Grant
- Patent Title: Reinforcement learning method, recording medium, and reinforcement learning system
-
Application No.: US16797515Application Date: 2020-02-21
-
Publication No.: US11543789B2Publication Date: 2023-01-03
- Inventor: Yoshihiro Okawa , Tomotake Sasaki , Hidenao Iwane , Hitoshi Yanami
- Applicant: FUJITSU LIMITED
- Applicant Address: JP Kawasaki
- Assignee: FUJITSU LIMITED
- Current Assignee: FUJITSU LIMITED
- Current Assignee Address: JP Kawasaki
- Agency: Xsensus LLP
- Priority: JPJP2019-039032 20190304
- Main IPC: G05B19/04
- IPC: G05B19/04 ; G05B19/042 ; G06N7/00 ; G06N20/00
Abstract:
A reinforcement learning method executed by a computer includes calculating a degree of risk for a state of a controlled object at a current time point with respect to a constraint condition related to the state of the controlled object, the degree of risk being calculated based on a predicted value of the state of the controlled object at a future time point, the predicted value being obtained from model information defining a relationship between the state of the controlled object and a control input to the controlled object; and determining the control input to the controlled object at the current time point, from a range defined according to the calculated degree of risk so that the range becomes narrower as the calculated degree of risk increases.
Public/Granted literature
- US20200285208A1 REINFORCEMENT LEARNING METHOD, RECORDING MEDIUM, AND REINFORCEMENT LEARNING SYSTEM Public/Granted day:2020-09-10
Information query
IPC分类:
