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
Intergenerational experimentation and catastrophic risk – Fikri Pitsuwan (Center of Economic Research, ETH Zurich)
I study an intergenerational game in which each generation experiments on a risky technology that provides private benefits, but may also cause a temporary catastrophe. I find a folk-theorem-type result on which there is a continuum of equilibria. Compared to the socially optimal level, some equilibria exhibit too much, while others too little, experimentation. The reason is that the payoff externality causes preemptive experimentation, while the informational externality leads to more caution…
Ethical Consumerism – Philip Trammell (Global Priorities Institute and Department of Economics, University of Oxford)
I study a static production economy in which consumers have not only preferences over their own consumption but also external, or “ethical”, preferences over the supply of each good. Though existing work on the implications of external preferences assumes price-taking, I show that ethical consumers generically prefer not to act even approximately as price-takers. I therefore introduce a near-Nash equilibrium concept that generalizes the near-Nash equilibria found in literature on strategic foundations of general equilibrium…
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’…