How to design the agents which have both continuous actions and discrete actions in Reinforcement Learning Toolbox?

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?

[Florian Kirschmann]

hello, did you find any answers to your question?

best regards