How do I save Episode Manager training data for *plotting* later

7 次查看（过去 30 天）
Rajesh Siraskar
Rajesh Siraskar 2021-1-1
编辑： Emmanouil Tzorakoleftherakis 2021-3-11
Hi,
Lets say I am using two algorithms to train for a task (DDPG and PPO). How do I save the data to plot a comparion later?
This is data like episode rewards, Q-value etc. plotted at every episode.
(Please note I am not referring to network weights for transfer learning.)

请先登录，再回答此问题。

采纳的回答

Rajesh Siraskar
Rajesh Siraskar 2021-1-5
编辑：Rajesh Siraskar 2021-1-5
Thank you Asvin and Emmanouil.
I didnt realize that I could store trainingStats and I can do anything with the data later. Awesome.
% Train the agent
trainingStats = train(agent, env, trainOpts);

更多回答（1 个）

Emmanouil Tzorakoleftherakis
编辑：Emmanouil Tzorakoleftherakis 2021-3-11
Hi Rajesh,
As mentioned in the comment above, if you are using R2020b, you can use
>> help rlPlotTrainingResults
to recreate the Episode manager plot.
If you are using R2021a, you may notice that this function is now renamed to "inspectTrainingResult".
Hope that helps

类别

在 Help Center 和 File Exchange 中查找有关 Reinforcement Learning 的更多信息

标签

产品


版本

R2020b

Community Treasure Hunt

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

Start Hunting!

Translated by