DDPG - Noise Model - sample time step - definition

Question

Niklas Reinisch 2019-8-2

1
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/474566-ddpg-noise-model-sample-time-step-definition

评论： Emmanouil Tzorakoleftherakis 2019-8-5

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 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Emmanouil Tzorakoleftherakis 2019-8-2

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/474566-ddpg-noise-model-sample-time-step-definition#answer_385979

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.