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
The evidentialist’s wager – William MacAskill, Aron Vallinder (Global Priorities Institute, Oxford University) Caspar Österheld (Duke University), Carl Shulman (Future of Humanity Institute, Oxford University), Johannes Treutlein (TU Berlin)
Suppose that an altruistic and morally motivated agent who is uncertain between evidential decision theory (EDT) and causal decision theory (CDT) finds herself in a situation in which the two theories give conflicting verdicts. We argue that even if she has significantly higher credence in CDT, she should nevertheless act …
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’…
The case for strong longtermism – Hilary Greaves and William MacAskill (Global Priorities Institute, University of Oxford)
A striking fact about the history of civilisation is just how early we are in it. There are 5000 years of recorded history behind us, but how many years are still to come? If we merely last as long as the typical mammalian species…