How do I save Episode Manager training data for *plotting* later
23 Ansichten (letzte 30 Tage)
Ältere Kommentare anzeigen
Rajesh Siraskar
am 1 Jan. 2021
Bearbeitet: Emmanouil Tzorakoleftherakis
am 11 Mär. 2021
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.)
1 Kommentar
Asvin Kumar
am 4 Jan. 2021
Would this be relevant to your question? https://www.mathworks.com/matlabcentral/answers/592492-reinforcement-learning-episode-manager#comment_1010239
Akzeptierte Antwort
Weitere Antworten (1)
Emmanouil Tzorakoleftherakis
am 4 Jan. 2021
Bearbeitet: Emmanouil Tzorakoleftherakis
am 11 Mär. 2021
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
0 Kommentare
Siehe auch
Kategorien
Mehr zu Training and Simulation finden Sie in Help Center und File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!