On Avoiding Power-Seeking by Artificial Intelligence

TL;DR

This paper explores how to design AI agents that limit their impact and avoid power-seeking behavior, proposing the AUP method and analyzing the incentives for power-seeking in various decision-making frameworks.

Contribution

Introduces the attainable utility preservation (AUP) method to promote conservative AI behavior and formalizes the problem of side effect avoidance and power-seeking incentives.

Findings

AUP produces conservative, option-preserving behavior in toy and complex environments.

Most reward functions lead to policies that resist deactivation or correction.

Power-seeking incentives are prevalent across various decision-making procedures.

Abstract

We do not know how to align a very intelligent AI agent's behavior with human interests. I investigate whether -- absent a full solution to this AI alignment problem -- we can build smart AI agents which have limited impact on the world, and which do not autonomously seek power. In this thesis, I introduce the attainable utility preservation (AUP) method. I demonstrate that AUP produces conservative, option-preserving behavior within toy gridworlds and within complex environments based off of Conway's Game of Life. I formalize the problem of side effect avoidance, which provides a way to quantify the side effects an agent had on the world. I also give a formal definition of power-seeking in the context of AI agents and show that optimal policies tend to seek power. In particular, most reward functions have optimal policies which avoid deactivation. This is a problem if we want to deactivate or correct an intelligent agent after we have deployed it. My theorems suggest that since most agent goals conflict with ours, the agent would very probably resist correction. I extend these theorems to show that power-seeking incentives occur not just for optimal decision-makers, but under a wide range of decision-making procedures.