Japan Intellectual Property Rights: LEARNING DEVICE, LEARNING METHOD AND LEARNING PROGRAM

Japan, Feb. 27 -- HITACHI LTD has got intellectual property rights for 'LEARNING DEVICE, LEARNING METHOD AND LEARNING PROGRAM.' Other related details are as follows:

Application Number: JP,2023-050157

Category (FI): G06F17/10@Z,G06N3/092

Stage: PROBLEM TO BE SOLVED: To guarantee stability of behavior in reinforcement learning.SOLUTION: A learning device including a processor for executing a program and a storage device for storing the program and training a neural network that learns a strategy for improving a first index, executes: problem generation processing of generating a convex optimization problem including a gradient function relating to a parameter update policy included in the neural network on the basis of information relating to the neural network; index generation processing of generating a second index relating to the policy on the basis of the convex optimization problem generated by the problem generation processing; and update processing of updating a parameter included in the neural network on the basis of the first index and the second index.SELECTED DRAWING: Figure 2 (Grant)

Filing Date: March 27, 2023

Publication Date: Oct. 9, 2024

The original document can be viewed at: https://www.j-platpat.inpit.go.jp/p0100

Disclaimer: Curated by HT Syndication.