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

PDF download

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

The long-run relationship between per capita incomes and population size – Maya Eden (University of Zurich) and Kevin Kuruc (Population Wellbeing Initiative, University of Texas at Austin)

The relationship between the human population size and per capita incomes has long been debated. Two competing forces feature prominently in these discussions. On the one hand, a larger population means that limited natural resources must be shared among more people. On the other hand, more people means more innovation and faster technological progress, other things equal. We study a model that features both of these channels. A calibration suggests that, in the long run, (marginal) increases in population would…

How to neglect the long term – Hayden Wilkinson (Global Priorities Institute, University of Oxford)

Consider longtermism: the view that, at least in some of the most important decisions facing agents today, which options are morally best is determined by which are best for the long-term future. Various critics have argued that longtermism is false—indeed, that it is obviously false, and that we can reject it on normative grounds without close consideration of certain descriptive facts. In effect, it is argued, longtermism would be false even if real-world agents had promising means…