Decision and action structure with ML agents (help needed)

Hello, I'm really new to ML agents and I don't know how it works very well.

After having some practice with some examples I decided to build one of my first projects using ML agents.

I want the IA to do two things, decide which actions to perform, and to realize the action it decided to.
As they will be multiple actions I want to do, I thought the best option would be to train every action as different IA's, and then train a central IA to decide which actions it should perform in different situations.

The concept itself is simple, but I can't even think on how to implement it.
I'll be trying to build a system that works like that, but I'm doubtful it may even be doable with ML agents, but I can't say nothing useful as I know almost nothing about ML agents.

I would thank any possible help, in building the system or finding alternatives.
Thanks in advance.