Save data in Deep RL in the Simulink environment for all episodes

Question

beni hadi 2021-1-6

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/710378-save-data-in-deep-rl-in-the-simulink-environment-for-all-episodes

评论： beni hadi 2021-1-16

Hello,

1) How to save the desired signal in all episodes in the deep reinforcement learning system implemented in the Simulink environment?

2) Is there a way to access the reward and average reward data per episode on the Simulink environment?

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 2021-1-16

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/710378-save-data-in-deep-rl-in-the-simulink-environment-for-all-episodes#answer_599510

Hello,

You can always select the signals you want to log and view them later in Simulation Data Inspector. Same goes for the reward signal since this is also effectively a Simulink signal. You need to be careful if training runs for a long time though, since you may end up saving several GBs worth of data.