DDPG - Noise Model - sample time step - definition
13 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
Niklas Reinisch
le 2 Août 2019
Commenté : Emmanouil Tzorakoleftherakis
le 5 Août 2019
Hello!
At the moment i am tuning the Parameters of my DDPG Algorithm and i don´t fully understand the Updating process of the Ornstein-Uhlenbeck Noise Model.
The Matlab Documentation describes the Process of Updating the Noise Model of a DDPG-algorithm, consisting of a Formula, which is used in every "sample time step".
(https://www.mathworks.com/help/reinforcement-learning/ref/rlddpgagentoptions.html Chapter: Input Arguments)
But how is the "sample time step" defined? Does this correlate with the episode or step count of the RL trainingprocess?
Thanks
Niklas
0 commentaires
Réponse acceptée
Emmanouil Tzorakoleftherakis
le 2 Août 2019
Hi Niklas,
This post should be helpful. By "sample time step" the documentation refers to the "step count of the RL trainingprocess", i.e. each episode consists of a number of time steps, and noise is applied to the selected action at the begining of each time step. See this link for a description of DDPG (and specifically step #1). The time step value can be specified in the agent options here.
2 commentaires
Emmanouil Tzorakoleftherakis
le 5 Août 2019
Correct. This is why you want to keep the decay rate small or zero if you want to promote exploration.
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!