DQN learns at first but then worsens.
8 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
Hi, I am training a DQN agent with a simevent model. I am testing out different hyperparameters, but everytime the agent learns (reward goes higher) at first for a while, but then goes down. I have tested different learning rate, exploration epsilon, and discount factors. But the shape of training progress is pretty much same in all combinations. Is there any potential way I can fix this issue?
0 commentaires
Réponses (1)
Emmanouil Tzorakoleftherakis
le 22 Avr 2021
Modifié(e) : Emmanouil Tzorakoleftherakis
le 22 Avr 2021
To confirm that this is an exploration issue, can you try setting the EpsilonMin param to a high value? e.g. 0.99. If after doing that you still see the same result, there is likely something else going on.
2 commentaires
Emmanouil Tzorakoleftherakis
le 23 Avr 2021
Hard to tell, but it's strange to me that the episode curve is similar every time. That makes me think that there is something specific about the way you have modeled your environment model that guides the training through a similar path each time.
Voir également
Catégories
En savoir plus sur Training and Simulation dans Help Center et File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!