Combining two deep neural networks to train simultaneously

Hello,

I have two deep neural networks that were trained individually. I would now like to combine them such that one recieves the action of the other as an input, then train them on the same reward. Is that possible? If so, how would I proceed about doing that?

Thank you.

Answer 1

[Emmanouil Tzorakoleftherakis]

Hello,

You can do this in Simulink - see the following examples for reference.

https://www.mathworks.com/help/reinforcement-learning/ug/train-2-agents-to-collaborate.html

https://www.mathworks.com/help/reinforcement-learning/ug/train-3-agents-for-area-coverage.html

https://www.mathworks.com/help/reinforcement-learning/ug/train-agents-for-path-following.html

[Jad Wehbeh]

Thank you