The way this is done in every domain where the real is a bottle neck is with simulation. So the actual argument is: What domains do we think are not practical to simulate even with extreme intelligence making the simulation and the ability to bring immense amounts of computing power to bear while running.
I don't think there are actually that many domains where you can't simulate them with enough knowledge and compute. So then the bottleneck becomes your ability to sample the world and refine your models. For some domains you can have the models run against each other in your sim which greatly reduces the need for real world feedback (see AlphaZero for example).
So in the case of human persuasion, like asking a boss for a raise, the model could of failed many times a second while trying to persuade a simulation of a typical middle manager with the same parameters as your boss.
I don't think there are actually that many domains where you can't simulate them with enough knowledge and compute. So then the bottleneck becomes your ability to sample the world and refine your models. For some domains you can have the models run against each other in your sim which greatly reduces the need for real world feedback (see AlphaZero for example).
So in the case of human persuasion, like asking a boss for a raise, the model could of failed many times a second while trying to persuade a simulation of a typical middle manager with the same parameters as your boss.