In this essay I will try to explain the overall structure and motivation of my AI alignment research agenda. The discussion is informal and no new theorems are proved here. The main features of my research agenda, as I explain them here, are

Viewing AI alignment theory as part of a general abstract theory of intelligence

Using desiderata and axiomatic definitions as starting points, rather than specific algorithms and constructions

Formulating alignment problems in the language of learning theory

Evaluating solutions by their formal mathematical properties, ultimately aiming at a quantitative theory of risk assessment

Relying on the mathematical intuition derived from learning theory to pave the way to solving philosophical questions

(Tiling result due to Sam, exposition of obstacles due to me)

Logical inductors of “similar strength”, playing against each other in a repeated game, will converge to correlated equilibria of the one-shot game, for the same reason that players that react to the past plays of their opponent converge to correlated equilibria. In fact, this proof is essentially just the proof from *Calibrated Learning and Correlated Equilibrium* by Forster (1997), adapted to a logical inductor setting.

In game theory, there are two different notions of “best response” at play. *Causal best-response* corresponds to standard game-theoretic reasoning, because it assumes that the joint probability distribution over everyone else’s moves remains unchanged if one player changes their move. The second one, *Evidential best-response*, can model cases where the actions of the various players are not subjectively independent, such as Death in Damascus, Twin Prisoner’s Dilemma, Troll Bridge, Newcomb, and Smoking Lesion, and will be useful to analyze the behavior of logical inductors in repeated games. This is just a quick rundown of the basic properties of these two notions of best response.

We introduce a variant of the concept of a “quantilizer” for the setting of choosing a policy for a finite Markov decision process (MDP), where the generic unknown cost is replaced by an unknown penalty term in the reward function. This is essentially a generalization of quantilization in repeated games with a cost independence assumption. We show that the “quantilal” policy shares some properties with the ordinary optimal policy, namely that (i) it can always be chosen to be Markov (ii) it can be chosen to be stationary when time discount is geometric (iii) the “quantilum” value of an MDP with geometric time discount is a continuous piecewise rational function of the parameters, and it converges when the discount parameter \(\lambda\) approaches 1. Finally, we demonstrate a polynomial-time algorithm for computing the quantilal policy, showing that quantilization is not qualitatively harder than ordinary optimization.

Reflective oracles can be approximated by computing Nash equilibria. But is there some procedure that produces a Pareto-optimal equilibrium in a game, aka, a point produced by a Cooperative oracle? It turns out there is. There are some interesting philosophical aspects to it, which will be typed up in the next post.

The result is not original to me, it’s been floating around MIRI for a while. I think Scott, Sam, and Abram worked on it, but there might have been others. All I did was formalize it a bit, and generalize from the 2-player 2-move case to the n-player n-move case. With the formalism here, it’s a bit hard to intuitively understand what’s going on, so I’ll indicate where to visualize an appropriate 3-dimensional object.

Crossposted at Lesserwrong.

**tl;dr**: if an agent has a biased learning process, it may choose actions that are worse (with certainty) for every possible reward function it could be learning.