22.2 主动增强学习 Active Reinforcement Learning | 奔三啦

[sheldon123z]

https://my-bucket-1302790708.cos-website.ap-guangzhou.myqcloud.com/2022/04/26/22-2/

Active learning 主动学习 Active ADP active ADP的更新公式 $$ U(s)=\max{a \in A(s)} \sum{s^{\prime}} P\left(s^{\prime} \mid s, a\right)\left[R\left(s, a, s^{\prime}\right)+\gamma U\left(s^{\prime}\right)\right

[sheldon123z]

测试一下

[sheldon123z]

效果拔群。。。

[liu-jinyu]

23333333