question about calculate loss value of dqn agent reinforcement learning
3 Ansichten (letzte 30 Tage)
Ältere Kommentare anzeigen
hello everyone,
I want to plot curve of loss value during training. It is not available in dqn training option directly as i know. My question is :
can i calculate loss simply with this function?
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/1419183/image.png)
Q0 is predicted value by critic. (orange line in default process-training plot)
EpisodeReward is gained reward by agent in t episode
t is number of episode
%% example code for loss plotting here
% unpack training statistic
index = trainingStats.EpisodeIndex;
reward = trainingStats.EpisodeReward;
pred_reward = trainingStats.EpisodeQ0;
Loss_Plot = [];
for t = 1:size(index, 1)
loss = (sum(pred_reward(1:t, 1)) - sum(reward(1:t, 1)))/t
Loss = [t, loss];
Loss_Plot = [Loss_Plot; Loss]
end
% plot curve
plot(Loss_Plot(:, 1), Loss_Plot(:, 2), '-')
can i plot loss value of episode with this example code properly?
thanks in advance.
Kun
1 Kommentar
Emmanouil Tzorakoleftherakis
am 27 Jun. 2023
Bearbeitet: Emmanouil Tzorakoleftherakis
am 27 Jun. 2023
Which version are you using? You can log loss data following the guidelines here: https://www.mathworks.com/help/reinforcement-learning/ug/log-training-data-to-disk.html
Antworten (0)
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!