Title:
知能客体強化学習方法、装置、デバイス、及び媒体
Document Type and Number:
Japanese Patent JP7163477
Kind Code:
B2
Abstract:
Embodiments of the present disclosure disclose an intelligent agent reinforcement learning method and apparatus, a device, and a medium. The method includes: acquiring key visual information on which an intelligent agent makes a policy for a current environment image; acquiring actual key visual information of the current environment image; determining attention variation reward information based on the key visual information and the actual key visual information; and adjusting reward feedback of reinforcement learning of the intelligent agent based on the attention variation reward information.
Inventors:
▲劉▼ 春▲曉▼
Hiroshi Xue
▲張▼ ▲偉▼
林 ▲チン▼
Hiroshi Xue
▲張▼ ▲偉▼
林 ▲チン▼
Application Number:
JP2021500797A
Publication Date:
October 31, 2022
Filing Date:
July 16, 2019
Export Citation:
Assignee:
SHENZHEN SENSETIME TECHNOLOGY CO., LTD.
International Classes:
G06N20/00
Domestic Patent References:
| JP2010287131A |
Foreign References:
| WO2018083672A1 |
Attorney, Agent or Firm:
Patent Business Corporation Unias International Patent Office
Previous Patent: Calcium phosphate curable composition, method for producing cured body, and cured body
Next Patent: ZIG FOR GRASPING
Next Patent: ZIG FOR GRASPING