DDPG - Noise Model - sample time step - definition
11 views (last 30 days)
Show older comments
Niklas Reinisch
on 2 Aug 2019
Commented: Emmanouil Tzorakoleftherakis
on 5 Aug 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 Comments
Accepted Answer
Emmanouil Tzorakoleftherakis
on 2 Aug 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 Comments
Emmanouil Tzorakoleftherakis
on 5 Aug 2019
Correct. This is why you want to keep the decay rate small or zero if you want to promote exploration.
More Answers (0)
See Also
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!