Intelligent Agent Foundations Forumsign up / log in
1.Reflective oracles as a solution to the converse Lawvere problem
post by Sam Eisenstat 62 days ago | Alex Mennen, Alex Appel, Vadim Kosoy, Abram Demski, Jessica Taylor, Scott Garrabrant and Vladimir Slepnev like this | discuss

1 Introduction

Before the work of Turing, one could justifiably be skeptical of the idea of a universal computable function. After all, there is no computable function \(f\colon\mathbb{N}\times\mathbb{N}\to\mathbb{N}\) such that for all computable \(g\colon\mathbb{N}\to\mathbb{N}\) there is some index \(i_{g}\) such that \(f\left(i_{g},n\right)=g\left(n\right)\) for all \(n\). If there were, we could pick \(g\left(n\right)=f\left(n,n\right)+1\), and then \[g\left(i_{g}\right)=f\left(i_{g},i_{g}\right)+1=g\left(i_{g}\right)+1,\] a contradiction. Of course, universal Turing machines don’t run into this obstacle; as Gödel put it, “By a kind of miracle it is not necessary to distinguish orders, and the diagonal procedure does not lead outside the defined notion.” [1]

The miracle of Turing machines is that there is a partial computable function \(f\colon\mathbb{N}\times\mathbb{N}\to\mathbb{N}\cup\left\{ \bot\right\}\) such that for all partial computable \(g\colon\mathbb{N}\to\mathbb{N}\cup\left\{ \bot\right\}\) there is an index \(i\) such that \(f\left(i,n\right)=g\left(n\right)\) for all \(n\). Here, we look at a different “miracle”, that of reflective oracles [2,3]. As we will see in Theorem 1, given a reflective oracle \(O\), there is a (stochastic) \(O\)-computable function \(f\colon\mathbb{N}\times\mathbb{N}\to\left\{ 0,1\right\}\) such that for any (stochastic) \(O\)-computable function \(g\colon\mathbb{N}\to\left\{ 0,1\right\}\), there is some index \(i\) such that \(f\left(i,n\right)\) and \(g\left(n\right)\) have the same distribution for all \(n\). This existence theorem seems to skirt even closer to the contradiction mentioned above.

We use this idea to answer “in spirit” the converse Lawvere problem posed in [4]. These methods also generalize to prove a similar analogue of the ubiquitous converse Lawvere problem from [5]. The original questions, stated in terms of topology, remain open, but I find that the model proposed here, using computability, is equally satisfying from the point of view of studying reflective agents. Those references can be consulted for more motivation on these problems from the perspective of reflective agency.

Section 3 proves the main lemma, and proves the converse Lawvere theorem for reflective oracles. In section 4, we use that to give a (circular) proof of Brouwer’s fixed point theorem, as mentioned in [4]. In section 5, we prove the ubiquitous converse Lawvere theorem for reflective oracles.

continue reading »
2.Announcing the AI Alignment Prize
link by Vladimir Slepnev 74 days ago | Vadim Kosoy likes this | discuss
3.Hyperreal Brouwer
post by Scott Garrabrant 104 days ago | Vadim Kosoy and Stuart Armstrong like this | 2 comments

This post explains how to view Kakutani’s fixed point theorem as a special case of Brouwer’s fixed point theorem with hyperreal numbers. This post is just math intuitions, but I found them useful in thinking about Kakutani’s fixed point theorem and many things in agent foundations. This came out of conversations with Sam Eisenstat.

continue reading »
4.Funding opportunity for AI alignment research
link by Paul Christiano 143 days ago | Vadim Kosoy likes this | 3 comments
5.The Three Levels of Goodhart's Curse
post by Scott Garrabrant 154 days ago | Vadim Kosoy, Abram Demski and Paul Christiano like this | 2 comments

Note: I now consider this post deprecated and instead recommend this updated version.

Goodhart’s curse is a neologism by Eliezer Yudkowsky stating that “neutrally optimizing a proxy measure U of V seeks out upward divergence of U from V.” It is related to many near by concepts (e.g. the tails come apart, winner’s curse, optimizer’s curse, regression to the mean, overfitting, edge instantiation, goodhart’s law). I claim that there are three main mechanisms through which Goodhart’s curse operates.

continue reading »
6.Open Problems Regarding Counterfactuals: An Introduction For Beginners
link by Alex Appel 183 days ago | Vadim Kosoy, Tsvi Benson-Tilsen, Vladimir Nesov and Wei Dai like this | 2 comments
7.Smoking Lesion Steelman
post by Abram Demski 199 days ago | Tom Everitt, Sam Eisenstat, Vadim Kosoy, Paul Christiano and Scott Garrabrant like this | 8 comments

It seems plausible to me that any example I’ve seen so far which seems to require causal/counterfactual reasoning is more properly solved by taking the right updateless perspective, and taking the action or policy which achieves maximum expected utility from that perspective. If this were the right view, then the aim would be to construct something like updateless EDT.

I give a variant of the smoking lesion problem which overcomes an objection to the classic smoking lesion, and which is solved correctly by CDT, but which is not solved by updateless EDT.

continue reading »
8.A cheating approach to the tiling agents problem
post by Vladimir Slepnev 201 days ago | Alex Mennen, Vadim Kosoy and Abram Demski like this | 2 comments

(This post resulted from a conversation with Wei Dai.)

Formalizing the tiling agents problem is very delicate. In this post I’ll show a toy problem and a solution to it, which arguably meets all the desiderata stated before, but only by cheating in a new and unusual way.

Here’s a summary of the toy problem: we ask an agent to solve a difficult math question and also design a successor agent. Then the successor must solve another math question and design its own successor, and so on. The questions get harder each time, so they can’t all be solved in advance, and each of them requires believing in Peano arithmetic (PA). This goes on for a fixed number of rounds, and the final reward is the number of correct answers.

Moreover, we will demand that the agent must handle both subtasks (solving the math question and designing the successor) using the same logic. Finally, we will demand that the agent be able to reproduce itself on each round, not just design a custom-made successor that solves the math question with PA and reproduces itself by quining.

continue reading »
9.Loebian cooperation in the tiling agents problem
post by Vladimir Slepnev 207 days ago | Alex Mennen, Vadim Kosoy, Abram Demski, Patrick LaVictoire and Stuart Armstrong like this | 4 comments

The tiling agents problem is about formalizing how AIs can create successor AIs that are at least as smart. Here’s a toy model I came up with, which is similar to Benya’s old model but simpler. A computer program X is asked one of two questions:

  • Would you like some chocolate?

  • Here’s the source code of another program Y. Do you accept it as your successor?

continue reading »
10.Cooperative Oracles: Stratified Pareto Optima and Almost Stratified Pareto Optima
post by Scott Garrabrant 229 days ago | Vadim Kosoy, Patrick LaVictoire and Stuart Armstrong like this | 8 comments

In this post, we generalize the notions in Cooperative Oracles: Nonexploited Bargaining to deal with the possibility of introducing extra agents that have no control but have preferences. We further generalize this to infinitely many agents. (Part of the series started here.)

continue reading »
11.Cooperative Oracles: Nonexploited Bargaining
post by Scott Garrabrant 250 days ago | Vadim Kosoy, Jessica Taylor, Patrick LaVictoire and Stuart Armstrong like this | 6 comments

In this post, we formalize and generalize the phenomenon described in the Eliezer Yudkowsky post Cooperating with agents with different ideas of fairness, while resisting exploitation. (Part of the series started here.)

continue reading »
12.Finding reflective oracle distributions using a Kakutani map
discussion post by Jessica Taylor 260 days ago | Vadim Kosoy likes this | discuss
13.A correlated analogue of reflective oracles
post by Jessica Taylor 261 days ago | Sam Eisenstat, Vadim Kosoy, Abram Demski and Scott Garrabrant like this | discuss

Summary: Reflective oracles correspond to Nash equilibria. A correlated version of reflective oracles exists and corresponds to correlated equilibria. The set of these objects is convex, which is useful.

continue reading »
14.Generalizing Foundations of Decision Theory II
post by Abram Demski 269 days ago | Sam Eisenstat, Vadim Kosoy, Jessica Taylor and Patrick LaVictoire like this | 4 comments

As promised in the previous post, I develop my formalism for justifying as many of the decision-theoretic axioms as possible with generalized dutch-book arguments. (I’ll use the term “generalized dutch-book” to refer to arguments with a family resemblance to dutch-book or money-pump.) The eventual goal is to relax these assumptions in a way which addresses bounded processing power, but for now the goal is to get as much of classical decision theory as possible justified by a generalized dutch-book.

continue reading »
15.Formal Open Problem in Decision Theory
post by Scott Garrabrant 293 days ago | Marcello Herreshoff, Sam Eisenstat, Vadim Kosoy, Jessica Taylor, Patrick LaVictoire and Stuart Armstrong like this | 13 comments

In this post, I present a new formal open problem. A positive answer would be valuable for decision theory research. A negative answer would be helpful, mostly for figuring out what is the closest we can get to a positive answer. I also give some motivation for the problem, and some partial progress.

Open Problem: Does there exist a topological space \(X\) (in some convenient category of topological spaces) such that there exists a continuous surjection from \(X\) to the space \([0,1]^X\) (of continuous functions from \(X\) to \([0,1]\))?

continue reading »
16.Generalizing Foundations of Decision Theory
discussion post by Abram Demski 325 days ago | Ryan Carey, Vadim Kosoy, Jessica Taylor and Scott Garrabrant like this | 8 comments
17.Entangled Equilibria and the Twin Prisoners' Dilemma
post by Scott Garrabrant 340 days ago | Vadim Kosoy and Patrick LaVictoire like this | 2 comments

In this post, I present a generalization of Nash equilibria to non-CDT agents. I will use this formulation to model mutual cooperation in a twin prisoners’ dilemma, caused by the belief that the other player is similar to you, and not by mutual prediction. (This post came mostly out of a conversation with Sam Eisenstat, as well as contributions from Tsvi Benson-Tilsen and Jessica Taylor)

continue reading »
18.Neural nets designing neural nets
link by Stuart Armstrong 364 days ago | Vadim Kosoy likes this | discuss
19.My current take on the Paul-MIRI disagreement on alignability of messy AI
post by Jessica Taylor 390 days ago | Ryan Carey, Vadim Kosoy, Daniel Dewey, Patrick LaVictoire, Scott Garrabrant and Stuart Armstrong like this | 40 comments

Paul Christiano and “MIRI” have disagreed on an important research question for a long time: should we focus research on aligning “messy” AGI (e.g. one found through gradient descent or brute force search) with human values, or on developing “principled” AGI (based on theories similar to Bayesian probability theory)? I’m going to present my current model of this disagreement and additional thoughts about it.

continue reading »
20.Uninfluenceable agents
post by Stuart Armstrong 405 days ago | Vadim Kosoy and Patrick LaVictoire like this | 7 comments

A putative new idea for AI control; index here.

After explaining biased learning processes, we can now define influenceable (and uninfluenceable) learning processes.

Recall that the (unbiased) influence problem is due to agents randomising their preferences, as a sort of artificial `learning’ process, if the real learning process is slow or incomplete.

continue reading »
21.The universal prior is malign
link by Paul Christiano 413 days ago | Ryan Carey, Vadim Kosoy, Jessica Taylor and Patrick LaVictoire like this | 4 comments
22.Online Learning 3: Adversarial bandit learning with catastrophes
post by Ryan Carey 429 days ago | Vadim Kosoy and Patrick LaVictoire like this | discuss

Note: This describes an idea of Jessica Taylor’s.

In order to better understand how machine learning systems might avoid catastrophic behavior, we are interested in modeling this as an adversarial learning problem.

continue reading »
23.Equilibria in adversarial supervised learning
post by Ryan Carey 459 days ago | Vadim Kosoy, Nate Soares and Patrick LaVictoire like this | discuss

Note: This describes an idea of Jessica Taylor’s.

continue reading »
24.Online Learning 1: Bias-detecting online learners
post by Ryan Carey 468 days ago | Vadim Kosoy, Jessica Taylor, Nate Soares and Paul Christiano like this | 7 comments

Note: This describes an idea of Jessica Taylor’s, and is the first of several posts about aspects of online learning.

continue reading »
25.In memoryless Cartesian environments, every UDT policy is a CDT+SIA policy
post by Jessica Taylor 585 days ago | Vadim Kosoy and Abram Demski like this | 1 comment

Summary: I define a memoryless Cartesian environments (which can model many familiar decision problems), note the similarity to memoryless POMDPs, and define a local optimality condition for policies, which can be roughly stated as “the policy is consistent with maximizing expected utility using CDT and subjective probabilities derived from SIA”. I show that this local optimality condition is necesssary but not sufficient for global optimality (UDT).

continue reading »
Older

NEW LINKS

NEW POSTS

NEW DISCUSSION POSTS

RECENT COMMENTS

This is somewhat related to
by Vadim Kosoy on The set of Logical Inductors is not Convex | 0 likes

This uses logical inductors
by Abram Demski on The set of Logical Inductors is not Convex | 0 likes

Nice writeup. Is one-boxing
by Tom Everitt on Smoking Lesion Steelman II | 0 likes

Hi Alex! The definition of
by Vadim Kosoy on Delegative Inverse Reinforcement Learning | 0 likes

A summary that might be
by Alex Appel on Delegative Inverse Reinforcement Learning | 1 like

I don't believe that
by Alex Appel on Delegative Inverse Reinforcement Learning | 0 likes

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 | 1 like

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

RSS

Privacy & Terms