Skip to content
This repository has been archived by the owner on Sep 5, 2021. It is now read-only.

Latest commit

 

History

History
21 lines (11 loc) · 348 Bytes

23-Day14.md

File metadata and controls

21 lines (11 loc) · 348 Bytes

WW14课程小结

05.25

http://101.6.161.107:8888/

强化学习

reinforcement learning

无监督的学习,基于智能体(Agent),从外界环境中通过交互不断学习,自我强化

State, Reward, Action

强化学习

  • 智能体的决策会影响环境

  • 长时间延时反馈

马尔科夫决策过程