How to implement the custom training with DQN agent in Simulink environment?

Hello, I would like to implement the custom RL DQN agent training in Simulink environment, I have tried to look into the references in the Custom Training Loop with Simulink Action Noise, while it is difficult to modify due to the different updating mechanism and lots of usage of local functions. Could you please help me a bit?

Thanks in advance

Answer 1

[Emmanouil Tzorakoleftherakis]

I would recommend looking at the doc first to see how custom loops/agents are structured. The following links should be helpful:

https://www.mathworks.com/help/reinforcement-learning/ug/custom-agents.html

https://www.mathworks.com/help/reinforcement-learning/ug/train-reinforcement-learning-policy-using-custom-training.html