I am worried that if you train both sides of playing an asymmetric game, you run into problems where you scale up at playing one side faster than playing the other side. This makes me think “The model after N+1 gradient updates isn’t that much better than model after N gradient updates.” is not enough of an assumption if you operationalize it in a way that ensures you are using the model to do the same thing in both cases, and if you don’t operationalize it in that way, it seem like too strong of an assumption.
I am worried that if you train both sides of playing an asymmetric game, you run into problems where you scale up at playing one side faster than playing the other side. This makes me think “The model after N+1 gradient updates isn’t that much better than model after N gradient updates.” is not enough of an assumption if you operationalize it in a way that ensures you are using the model to do the same thing in both cases, and if you don’t operationalize it in that way, it seem like too strong of an assumption.
I agree that asymmetric games are the interesting case, and it’s rare you can use an assumption this weak.