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
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
Meaning, medicine and merit – Andreas Mogensen (Global Priorities Institute, Oxford University)
Given the inevitability of scarcity, should public institutions ration healthcare resources so as to prioritize those who contribute more to society? Intuitively, we may feel that this would be somehow inegalitarian. I argue that the egalitarian objection to prioritizing treatment on the basis of patients’ usefulness to others is best thought…
The Shutdown Problem: An AI Engineering Puzzle for Decision Theorists – Elliott Thornley (Global Priorities Institute, University of Oxford)
I explain and motivate the shutdown problem: the problem of designing artificial agents that (1) shut down when a shutdown button is pressed, (2) don’t try to prevent or cause the pressing of the shutdown button, and (3) otherwise pursue goals competently. I prove three theorems that make the difficulty precise. These theorems suggest that agents satisfying some innocuous-seeming conditions will often try to prevent or cause the pressing of the shutdown button, even in cases where it’s costly to do so. I end by noting that…
Are we living at the hinge of history? – William MacAskill (Global Priorities Institute, Oxford University)
In the final pages of On What Matters, Volume II, Derek Parfit comments: ‘We live during the hinge of history… If we act wisely in the next few centuries, humanity will survive its most dangerous and decisive period… What now matters most is that we avoid ending human history.’ This passage echoes Parfit’s comment, in Reasons and Persons, that ‘the next few centuries will be the most important in human history’. …