How to design the agents which have both continuous actions and discrete actions in Reinforcement Learning Toolbox?
1 visualizzazione (ultimi 30 giorni)
Mostra commenti meno recenti
I want to use the DDPG in Reinforcement Learning Toolbox to train the agents. The states in the agents are continuous. However, the actions in the agents both include the continuous ones and the discrete ones. How to define such kind of agents and how to design the corresponding training processes? Is there any example for me to refer?
1 Commento
Risposte (0)
Vedere anche
Prodotti
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!