INFORMATION PROCESSOR, INFORMATION PROCESSING METHOD, AND PROVIDING MEDIUM

Title:

INFORMATION PROCESSOR, INFORMATION PROCESSING METHOD, AND PROVIDING MEDIUM

Document Type and Number:

WIPO Patent Application WO/2000/010098

Kind Code:

A1

Abstract:

At step S1, a prediction operation to confer a maximum reward is carried out in a recurrent neural network by a forward dynamics. At step S2, a plan is made by a reverse dynamics. Thus, an action plan constituted of a sequence of differential values of an action for conferring the maximum reward. The steps are repeated until it is judged that a desired action plan is made at step S3. In such a way, an action plan which maximizes the reward is generated from a few action experiences.

Inventors:

TANI JUN (JP)

Application Number:

PCT/JP1999/004306

Publication Date:

February 24, 2000

Filing Date:

August 09, 1999

Export Citation:

Click for automatic bibliography generation Help

Assignee:

SONY CORP (JP)
TANI JUN (JP)

International Classes:

G06F15/18; B25J13/00; G05B13/02; G05D1/02; G06N3/00; (IPC1-7): G06F15/18; G05B13/00

Foreign References:

JPH07244502A	1995-09-19
JPH06324710A	1994-11-25
JPH09245012A	1997-09-19
US5608843A	1997-03-04

Attorney, Agent or Firm:

Koike, Akira (Toranomon 2-chome Minato-ku Tokyo, JP)

Download PDF:

View/Download PDF PDF Help

Previous Patent: UNIVERSAL BUSINESS MANAGEMENT SYSTEM AND METHOD

Next Patent: COMPUTER ARCHITECTURE AND PROCESS FOR AUDIO CONFERENCING OVER LOCAL AND GLOBAL NETWORKS INCLUDING IN...