Input normalization using a reinforcement learning DQN agent

Question

Margarita Cabrera 2021-3-26

1
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/784636-input-normalization-using-a-reinforcement-learning-dqn-agent

评论： H. M. 2022-12-3

采纳的回答： Emmanouil Tzorakoleftherakis

Hi all

I have built a DQN agent to solv a custom reinforcement problem.

Following mathworks examples I have no used any kind of normalization applied to the critic input.

In fact, as far as I could check, all examples of RL that use a DNN to create an actor or a critic especify 'Normalization', 'none' at the input layers of the Actor and Critic.

My question is, is it possible to use a normalization as for instance "zscore" at the input layers of a critic or of an actor when these are based on a DNN?

I'have tried to applied zscore normalization, but then, the agent does not work.

thanks

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Emmanouil Tzorakoleftherakis 2021-3-26

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/784636-input-normalization-using-a-reinforcement-learning-dqn-agent#answer_659521

Hello,

Normalization through the input layers is not supported for RL training. As a workaround, you can scale the observations rewards on the environment side.

2 个评论
显示无隐藏无

Margarita Cabrera 2021-3-27

Ok, thanks

H. M. 2022-12-3

@Emmanouil Tzorakoleftherakis

Could you explain more, the way you mentioned about normalization. I want to do it, but I can't figure it out.

Regards

请先登录，再进行评论。

Input normalization using a reinforcement learning DQN agent

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

采纳的回答

2 个评论
显示无隐藏无

更多回答（0 个）

另请参阅

类别

标签

产品

Community Treasure Hunt

Input normalization using a reinforcement learning DQN agent

0 个评论 显示 -2更早的评论隐藏 -2更早的评论

采纳的回答

2 个评论 显示 无隐藏 无

更多回答（0 个）

另请参阅

类别

标签

产品

Community Treasure Hunt

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

2 个评论
显示无隐藏无