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
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…
Quadratic Funding with Incomplete Information – Luis M. V. Freitas (Global Priorities Institute, University of Oxford) and Wilfredo L. Maldonado (University of Sao Paulo)
Quadratic funding is a public good provision mechanism that satisfies desirable theoretical properties, such as efficiency under complete information, and has been gaining popularity in practical applications. We evaluate this mechanism in a setting of incomplete information regarding individual preferences, and show that this result only holds under knife-edge conditions. We also estimate the inefficiency of the mechanism in a variety of settings and show, in particular, that inefficiency increases…
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…