Towards shutdownable agents via stochastic choice

Elliott Thornley (Global Priorities Institute, University of Oxford), Alexander Roman (New College of Florida), Christos Ziakas (Independent), Leyton Ho (Brown University) and Louis Thomson (University of Oxford)

GPI Working Paper No. 16-2024

Some worry that advanced artificial agents may resist being shut down. The Incomplete Preferences Proposal (IPP) is an idea for ensuring that doesn’t happen. 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 suggest that DREST reward functions could also train advanced agents to be USEFUL and NEUTRAL, and thereby make these advanced agents useful and shutdownable.

Other working papers

Estimating long-term treatment effects without long-term outcome data – David Rhys Bernard (Rethink Priorities), Jojo Lee and Victor Yaneng Wang (Global Priorities Institute, University of Oxford)

The surrogate index method allows policymakers to estimate long-run treatment effects before long-run outcomes are observable. We meta-analyse this approach over nine long-run RCTs in development economics, comparing surrogate estimates to estimates from actual long-run RCT outcomes. We introduce the M-lasso algorithm for constructing the surrogate approach’s first-stage predictive model and compare its performance with other surrogate estimation methods. …

A paradox for tiny probabilities and enormous values – Nick Beckstead (Open Philanthropy Project) and Teruji Thomas (Global Priorities Institute, Oxford University)

We show that every theory of the value of uncertain prospects must have one of three unpalatable properties. Reckless theories recommend risking arbitrarily great gains at arbitrarily long odds for the sake of enormous potential; timid theories recommend passing up arbitrarily great gains to prevent a tiny increase in risk; nontransitive theories deny the principle that, if A is better than B and B is better than C, then A must be better than C.

Welfare and felt duration – Andreas Mogensen (Global Priorities Institute, University of Oxford)

How should we understand the duration of a pleasant or unpleasant sensation, insofar as its duration modulates how good or bad the experience is overall? Given that we seem able to distinguish between subjective and objective duration and that how well or badly someone’s life goes is naturally thought of as something to be assessed from her own perspective, it seems intuitive that it is subjective duration that modulates how good or bad an experience is from the perspective of an individual’s welfare. …