Title:
DEEP REINFORCEMENT LEARNING-BASED ADAPTIVE GAME ALGORITHM
Document Type and Number:
WIPO Patent Application WO/2020/024097
Kind Code:
A1
Abstract:
The present invention relates to the field of data processing, and discloses a deep reinforcement learning-based adaptive game algorithm, comprising the following steps: (A) acquiring policies for different degrees of cooperation; (B) generating policies for different degrees of cooperation; (C) detecting a cooperation policy of an opponent; and (D) making different coping policies. The technical effects of the present invention are as follows: trained detectors and policies for different degrees of cooperation are used to implement the existing concepts, such as Tit for tat, in sequential social dilemmas, improving the extensibility of the agent, and more intuitively acquiring competition policies superior to those already acquired.
Inventors:
HOU HANXU (CN)
HAO JIANYE (CN)
WANG WEIXUN (CN)
HAO JIANYE (CN)
WANG WEIXUN (CN)
Application Number:
PCT/CN2018/097747
Publication Date:
February 06, 2020
Filing Date:
July 30, 2018
Export Citation:
Assignee:
UNIV DONGGUAN TECHNOLOGY (CN)
International Classes:
G06N3/02; G05B13/04
Foreign References:
| CN107479380A | 2017-12-15 | |||
| CN103500361A | 2014-01-08 | |||
| CN107479380A | 2017-12-15 | |||
| CN103500361A | 2014-01-08 | |||
| CN106371318A | 2017-02-01 |
Attorney, Agent or Firm:
SZ KINDWALF INTELLECTUAL PROPERTY FIRM (CN)
Download PDF: