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

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.)

[Asvin Kumar]

Would this be relevant to your question? https://www.mathworks.com/matlabcentral/answers/592492-reinforcement-learning-episode-manager#comment_1010239

Answer 1

[Rajesh Siraskar]

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);

Answer 2

[Emmanouil Tzorakoleftherakis]

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