Intelligent Agent Foundations Forumsign up / log in
by Jessica Taylor 367 days ago | link | parent

Because of the specific time restriction, there is no way to randomise the outcome ahead of time. And because it’s assumed tied to a specific physical event, there is no way to influence it at all. The whole physical definition and apparatus serve the purpose of making biasing the only way to affect the result.

Hmm, I don’t understand. Of course it is possible to influence the button push without biasing it (e.g. create a robot that flips a coin and then pushes or doesn’t push the button). And of course it’s not possible to influence the quantum event in any way (including by biasing it). So I don’t see any event that can’t be influenced in any way except by biasing it.



by Stuart Armstrong 366 days ago | link

The way I’m using the term, unbiased influence involves replacing the stochastic event with another one that has same mean. But since (or if) the quantum event is specifically defined in the process, this can’t be done.

reply

by Jessica Taylor 366 days ago | link

Let me ask a more specific question. In your setup with the quantum event \(Q\) and the button \(B\), can you define the event \(E\) such that:

  1. The agent can influence \(E\) by biasing \(E\).
  2. The agent can’t influence \(E\) without biasing \(E\).

Clearly, \(E \neq Q\) and \(E \neq B\), so I don’t know what \(E\) is. (I interpreted you as saying there is such an \(E\); let me know if this is incorrect)

reply

by Stuart Armstrong 359 days ago | link

You are correct and I’m wrong. The causal counterfactual is unbiased and uninfluenceable. The evidential counterfactual is both biased and influenceable. I’ll correct the post.

reply



NEW LINKS

NEW POSTS

NEW DISCUSSION POSTS

RECENT COMMENTS

This is exactly the sort of
by Stuart Armstrong on Being legible to other agents by committing to usi... | 0 likes

When considering an embedder
by Jack Gallagher on Where does ADT Go Wrong? | 0 likes

The differences between this
by Abram Demski on Policy Selection Solves Most Problems | 0 likes

Looking "at the very
by Abram Demski on Policy Selection Solves Most Problems | 0 likes

Without reading closely, this
by Paul Christiano on Policy Selection Solves Most Problems | 1 like

>policy selection converges
by Stuart Armstrong on Policy Selection Solves Most Problems | 0 likes

Indeed there is some kind of
by Vadim Kosoy on Catastrophe Mitigation Using DRL | 0 likes

Very nice. I wonder whether
by Vadim Kosoy on Hyperreal Brouwer | 0 likes

Freezing the reward seems
by Vadim Kosoy on Resolving human inconsistency in a simple model | 0 likes

Unfortunately, it's not just
by Vadim Kosoy on Catastrophe Mitigation Using DRL | 0 likes

>We can solve the problem in
by Wei Dai on The Happy Dance Problem | 1 like

Maybe it's just my browser,
by Gordon Worley III on Catastrophe Mitigation Using DRL | 2 likes

At present, I think the main
by Abram Demski on Looking for Recommendations RE UDT vs. bounded com... | 0 likes

In the first round I'm
by Paul Christiano on Funding opportunity for AI alignment research | 0 likes

Fine with it being shared
by Paul Christiano on Funding opportunity for AI alignment research | 0 likes

RSS

Privacy & Terms