I have read many blog articles, research papers and watched many youtube videos, but it seems it is hard to find why experience replay is efficient.

I know that the experience replay stores (state, action, reward, newstate) and sample minibatch and update weights, however, what I don't understand is how come the bellman equation can be the target value and how the learning can be done with supervised learning the value of (reward + gamma * (maximum next action)) being target?

It would be great if you can suggest any articles or videos? or explain it.


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.