更新算法模版

This commit is contained in:
johnjim0816
2022-11-06 12:15:36 +08:00
parent 466a17707f
commit dc78698262
256 changed files with 17282 additions and 10229 deletions

View File

@@ -0,0 +1,7 @@
## 脚本描述
* `task0.py`:离散动作任务
* `task1.py`:离散动作任务,与`task0.py`唯一的区别就是Actor的激活函数是tanh而不是relu`CartPole-v1`上效果更好
* `task2.py`:连续动作任务,#TODO待调试