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 does not 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

Choosing the future: Markets, ethics and rapprochement in social discounting – Antony Millner (University of California, Santa Barbara) and Geoffrey Heal (Columbia University)

This paper provides a critical review of the literature on choosing social discount rates (SDRs) for public cost-benefit analysis. We discuss two dominant approaches, the first based on market prices, and the second based on intertemporal ethics. While both methods have attractive features, neither is immune to criticism. …

The epistemic challenge to longtermism – Christian Tarsney (Global Priorities Institute, Oxford University)

Longtermists claim that what we ought to do is mainly determined by how our actions might affect the very long-run future. A natural objection to longtermism is that these effects may be nearly impossible to predict— perhaps so close to impossible that, despite the astronomical importance of the far future, the expected value of our present actions is mainly determined by near-term considerations. This paper aims to precisify and evaluate one version of this epistemic objection to longtermism…

How much should governments pay to prevent catastrophes? Longtermism’s limited role – Carl Shulman (Advisor, Open Philanthropy) and Elliott Thornley (Global Priorities Institute, University of Oxford)

Longtermists have argued that humanity should significantly increase its efforts to prevent catastrophes like nuclear wars, pandemics, and AI disasters. But one prominent longtermist argument overshoots this conclusion: the argument also implies that humanity should reduce the risk of existential catastrophe even at extreme cost to the present generation. This overshoot means that democratic governments cannot use the longtermist argument to guide their catastrophe policy. …