Why is the DDPG episode rewards never change during the whole training process?
7 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
Guoge Tan
le 25 Mai 2020
Commenté : Shahriar
le 29 Juin 2022
I'm training a DDPG agent using the Reinforcement Learning toolbox on MATLAB R2020a for a path planning problem. But as you can see, the DDPG episode rewards and average rewards never change during 5000 episodes. I used a simple neural networks with 20 neurons and three layers, the learning rate is set to 0.01, and the Gradient Threshold is 1. Then I try to set weights and bias for fully connected layers and change my reward function, but the result is the same.
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/300253/image.png)
1 commentaire
Réponse acceptée
Emmanouil Tzorakoleftherakis
le 26 Mai 2020
Looks like the scale between Q0 and episode reward is very different. Try unchecking "Show Episode Q0" to see of the episode reward changes. I would then simplify the critic network to make sure it outputs values in a similar scale as the episode reward.
0 commentaires
Plus de réponses (0)
Voir également
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!