New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add option for concatenation of data for training #6

Open

nikos-kekatos opened this issue May 4, 2020 · 0 comments

Owner

nikos-kekatos commented May 4, 2020

Using Simulink for simulation produces d_i={ref, u, y}
$i \in [1..m]$ where $m$ is the number of simulation traces

D_ref=[ref₁, ref₂, ..., ref_m]
similarly D_u, D_y are defined. Then, D={D_ref, D_u, D_y}.

However, the input of the NN at step k might include previous values of ref, u, or y, e.g. ref(k), ref(k-1).

Concatenating these values requires making the previous values 0. However, this is only done for the first trace and not for i=[2,..m]

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment