Skip to content

Commit

Permalink
docs: 📝 Updated reademe.md
Browse files Browse the repository at this point in the history
  • Loading branch information
Phoenix-Shen committed Nov 2, 2023
1 parent 64a5fab commit 53159fd
Showing 1 changed file with 2 additions and 1 deletion.
3 changes: 2 additions & 1 deletion readme.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@

## 写在前面

- 2023.11.02: 有很多人反映gym代码报错,这是因为Gym新版本调用`env.step(),env.reset()`返回的值多了一个东西,详情请见[这个issue](https://github.com/Phoenix-Shen/ReinforcementLearning/issues/3),解决方法是修改代码,或者按照我提供的requirements.txt安装环境。
- Note that the algorithm code comes from some experts in the field of reinforcement learning or I refactored the algorithms myself.

- 本仓库中的强化学习算法来自于Medium、YouTube、CSDN等等网站,详细的信息请见该readme下面的“参考资料”这一小节,或许会对您有些帮助。
Expand Down Expand Up @@ -739,7 +740,7 @@ def forward(self, x: t.Tensor) -> t.Tensor:

#### 3. REINFORCE with Baseline

- 关于baseline可以在[策略学习](#3-策略学习-policy-based-learning---学习策略-pias)这里看到
- 关于baseline可以在[策略学习](#3-策略学习-policy-based-learning---学习策略)这里看到

- 我们有随机策略梯度:
$$
Expand Down

0 comments on commit 53159fd

Please sign in to comment.