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
Maximal cluelessness – Andreas Mogensen (Global Priorities Institute, Oxford University)
I argue that many of the priority rankings that have been proposed by effective altruists seem to be in tension with apparently reasonable assumptions about the rational pursuit of our aims in the face of uncertainty. The particular issue on which I focus arises from recognition of the overwhelming importance…
Non-additive axiologies in large worlds – Christian Tarsney and Teruji Thomas (Global Priorities Institute, Oxford University)
Is the overall value of a world just the sum of values contributed by each value-bearing entity in that world? Additively separable axiologies (like total utilitarianism, prioritarianism, and critical level views) say ‘yes’, but non-additive axiologies (like average utilitarianism, rank-discounted utilitarianism, and variable value views) say ‘no’…
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…