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
On two arguments for Fanaticism – Jeffrey Sanford Russell (University of Southern California)
Should we make significant sacrifices to ever-so-slightly lower the chance of extremely bad outcomes, or to ever-so-slightly raise the chance of extremely good outcomes? Fanaticism says yes: for every bad outcome, there is a tiny chance of of extreme disaster that is even worse, and for every good outcome, there is a tiny chance of an enormous good that is even better.
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’…
Funding public projects: A case for the Nash product rule – Florian Brandl (Stanford University), Felix Brandt (Technische Universität München), Dominik Peters (University of Oxford), Christian Stricker (Technische Universität München) and Warut Suksompong (National University of Singapore)
We study a mechanism design problem where a community of agents wishes to fund public projects via voluntary monetary contributions by the community members. This serves as a model for public expenditure without an exogenously available budget, such as participatory budgeting or voluntary tax programs, as well as donor coordination when interpreting charities as public projects and donations as contributions. Our aim is to identify a mutually beneficial distribution of the individual contributions. …