bacow/easy-rl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update chapter8_questions&keywords.md

Browse Source
This commit is contained in:
David Young
2021-02-07 22:35:37 +08:00
committed by GitHub
parent 517fbfb4d5
commit 2d116a5019
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/chapter8/chapter8_questions&keywords.md
View File

@@ -1,6 +1,6 @@
# Chapter8 Q-learning for Continuous Actions # Chapter8 Q-learning for Continuous Actions
## 思考题 ## Questions
- Q-learning相比于policy gradient based方法为什么训练起来效果更好，更平稳？ - Q-learning相比于policy gradient based方法为什么训练起来效果更好，更平稳？