enter image description here

I'm implementing DDQN in my toy scenario. During training, I'm surprised to see that the total reward doesn't converge and have a tendency to degrade. What could be the problem?

Here's the picture: episode reward vs # of episodes during the training process.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.