I actually think that the Imitation Problem should not be resolved in the direction of taking action a. Otherwise it seems like Omega could tell the agent that it is going to shortly take action a, the agent will conclude that a must be safe, and it will then take action a… but a can be arbitrary here!
Basically, I think a solution to Vingean reflection ought to ensure that the reasoning process is well-founded: for every decision, we want to be sure that some particular version of the agent has actually done the necessary verification work rather than passing the buck. (For that reason, I do think that model polymorphism is on the right track.)
I think we can address this by assuming that the agent is imitating a copy who made the decision on its own rather than by imitating; I’ve edited the post to reflect this additional stipulation.
I actually think that the Imitation Problem should not be resolved in the direction of taking action a. Otherwise it seems like Omega could tell the agent that it is going to shortly take action a, the agent will conclude that a must be safe, and it will then take action a… but a can be arbitrary here!
Basically, I think a solution to Vingean reflection ought to ensure that the reasoning process is well-founded: for every decision, we want to be sure that some particular version of the agent has actually done the necessary verification work rather than passing the buck. (For that reason, I do think that model polymorphism is on the right track.)
I think we can address this by assuming that the agent is imitating a copy who made the decision on its own rather than by imitating; I’ve edited the post to reflect this additional stipulation.