Intelligent Agent Foundations Forumsign up / log in
by Patrick LaVictoire 1476 days ago | link | parent

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.)



by Abram Demski 1475 days ago | link

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.

reply



NEW LINKS

NEW POSTS

NEW DISCUSSION POSTS

RECENT COMMENTS

[Note: This comment is three
by Ryan Carey on A brief note on factoring out certain variables | 0 likes

There should be a chat icon
by Alex Mennen on Meta: IAFF vs LessWrong | 0 likes

Apparently "You must be
by Jessica Taylor on Meta: IAFF vs LessWrong | 1 like

There is a replacement for
by Alex Mennen on Meta: IAFF vs LessWrong | 1 like

Regarding the physical
by Vanessa Kosoy on The Learning-Theoretic AI Alignment Research Agend... | 0 likes

I think that we should expect
by Vanessa Kosoy on The Learning-Theoretic AI Alignment Research Agend... | 0 likes

I think I understand your
by Jessica Taylor on The Learning-Theoretic AI Alignment Research Agend... | 0 likes

This seems like a hack. The
by Jessica Taylor on The Learning-Theoretic AI Alignment Research Agend... | 0 likes

After thinking some more,
by Vanessa Kosoy on The Learning-Theoretic AI Alignment Research Agend... | 0 likes

Yes, I think that we're
by Vanessa Kosoy on The Learning-Theoretic AI Alignment Research Agend... | 0 likes

My intuition is that it must
by Vanessa Kosoy on The Learning-Theoretic AI Alignment Research Agend... | 0 likes

To first approximation, a
by Vanessa Kosoy on The Learning-Theoretic AI Alignment Research Agend... | 0 likes

Actually, I *am* including
by Vanessa Kosoy on The Learning-Theoretic AI Alignment Research Agend... | 0 likes

Yeah, when I went back and
by Alex Appel on Optimal and Causal Counterfactual Worlds | 0 likes

> Well, we could give up on
by Jessica Taylor on The Learning-Theoretic AI Alignment Research Agend... | 0 likes

RSS

Privacy & Terms