Towards shutdownable agents via stochastic choice
Elliott Thornley (Global Priorities Institute, University of Oxford), Alexander Roman (New College of Florida), Christos Ziakas (Imperial College, London), Leyton Ho (Brown University) and Louis Thomson (University of Oxford)
GPI Working Paper No. 16-2024
The Incomplete Preferences Proposal (IPP) is an idea for ensuring that advanced artificial agents never resist shutdown. A key part of the IPP is using a novel ‘Discounted Reward for Same-Length Trajectories (DReST)’ reward function to train agents to (1) pursue goals effectively conditional on each trajectory-length (be ‘USEFUL’), and (2) choose stochastically between different trajectory-lengths (be ‘NEUTRAL’ about trajectory-lengths). In this paper, we propose evaluation metrics for USEFULNESS and NEUTRALITY. We use a DReST reward function to train simple agents to navigate gridworlds, and we find that these agents learn to be USEFUL and NEUTRAL. Our results thus provide some initial evidence that DReST reward functions could train advanced agents to be USEFUL and NEUTRAL. Our theoretical work suggests that these agents would be useful and shutdownable.
Other working papers
Is Existential Risk Mitigation Uniquely Cost-Effective? Not in Standard Population Models – Gustav Alexandrie (Global Priorities Institute, University of Oxford) and Maya Eden (Brandeis University)
What socially beneficial causes should philanthropists prioritize if they give equal ethical weight to the welfare of current and future generations? Many have argued that, because human extinction would result in a permanent loss of all future generations, extinction risk mitigation should be the top priority given this impartial stance. Using standard models of population dynamics, we challenge this conclusion. We first introduce a theoretical framework for quantifying undiscounted cost-effectiveness over…
It Only Takes One: The Psychology of Unilateral Decisions – Joshua Lewis (New York University) et al.
Sometimes, one decision can guarantee that a risky event will happen. For instance, it only took one team of researchers to synthesize and publish the horsepox genome, thus imposing its publication even though other researchers might have refrained for biosecurity reasons. We examine cases where everybody who can impose a given event has the same goal but different information about whether the event furthers that goal. …
Concepts of existential catastrophe – Hilary Greaves (University of Oxford)
The notion of existential catastrophe is increasingly appealed to in discussion of risk management around emerging technologies, but it is not completely clear what this notion amounts to. Here, I provide an opinionated survey of the space of plausibly useful definitions of existential catastrophe. Inter alia, I discuss: whether to define existential catastrophe in ex post or ex ante terms, whether an ex ante definition should be in terms of loss of expected value or loss of potential…