Soft Actor Critic deploy mean path only

2021 5 6
1 个回答
回答已采纳
更新时间：2021 5 13
2 次查看（30 天）

0 个投票

Hi, I'm wondering if there's a way to only deploy the mean path of the SAC agent after it's been trained? This is useful to create more stable actions after the network has been trained.
Should I extract the network weights manually, create a network, then extract an output path for the mean network?

请先登录，再回答此问题。

 采纳的回答

0 个投票

Hello,
Please take a look at this option here which was added in R2021a to allow exactly the behavior you mentioned.
Hope this helps

1 个评论
显示 -1更早的评论 隐藏 -1更早的评论

Tech Logg Ding
Tech Logg Ding 2021-5-13
编辑：Tech Logg Ding 2021-5-13
Thank you for the reply. That setting works. I've also tried the roundabout way of extracting the actor neural network and modifying it to only have the mean path. Then I deploy the actor neural network into the simulation to act as a controller. Both method works!

请先登录，再进行评论。

更多回答（0 个）

类别

在 帮助中心 和 File Exchange 中查找有关 Reinforcement Learning 的更多信息

产品

版本

R2021a

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by