- 专利标题: TRAINING ARCHITECTURE USING GAME CONSOLES
-
申请号: US17650275申请日: 2022-02-08
-
公开(公告)号: US20230249082A1公开(公告)日: 2023-08-10
- 发明人: Peter Wurman , Leon Barrett , Piyush Khandelwal , Dion Whitehead , Rory Douglas , Houmehr Aghabozorgi , Justin V Beltran , Rabih Abdul Ahad , Bandaly Azzam
- 申请人: Sony Group Corporation , Sony Corporation of America , Sony Interactive Entertainment LLC
- 申请人地址: JP NY Tokyo
- 专利权人: Sony Group Corporation,Sony Corporation of America,Sony Interactive Entertainment LLC
- 当前专利权人: Sony Group Corporation,Sony Corporation of America,Sony Interactive Entertainment LLC
- 当前专利权人地址: JP NY Tokyo
- 主分类号: A63F13/67
- IPC分类号: A63F13/67 ; A63F13/352 ; G06F8/71
摘要:
An artificial intelligent agent can act as a player in a video game, such as a racing video game. The agent can race against, and often beat, the best players in the world. The game can be completely external to the agent and can run in real time. In this way, the training system is much more like a real world system. The consoles on which the game runs for training the agent are provided in a cloud computing environment. The agents and the trainers can run on other computing devices in the cloud, where the system can choose the trainers and agent compute based on proximity to console, for example. Users can choose the game they want to run and submit code which can be built and deployed to the cloud system. Metrics and logs and artifacts from the game can be sent to cloud storage.
信息查询