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
Tough enough? Robust satisficing as a decision norm for long-term policy analysis – Andreas Mogensen and David Thorstad (Global Priorities Institute, Oxford University)
This paper aims to open a dialogue between philosophers working in decision theory and operations researchers and engineers whose research addresses the topic of decision making under deep uncertainty. Specifically, we assess the recommendation to follow a norm of robust satisficing when making decisions under deep uncertainty in the context of decision analyses that rely on the tools of Robust Decision Making developed by Robert Lempert and colleagues at RAND …
The Conservation Multiplier – Bård Harstad (University of Oslo)
Every government that controls an exhaustible resource must decide whether to exploit it or to conserve and thereby let the subsequent government decide whether to exploit or conserve. This paper develops a positive theory of this situation and shows when a small change in parameter values has a multiplier effect on exploitation. The multiplier strengthens the influence of a lobby paying for exploitation, and of a donor compensating for conservation. …
Three mistakes in the moral mathematics of existential risk – David Thorstad (Global Priorities Institute, University of Oxford)
Longtermists have recently argued that it is overwhelmingly important to do what we can to mitigate existential risks to humanity. I consider three mistakes that are often made in calculating the value of existential risk mitigation: focusing on cumulative risk rather than period risk; ignoring background risk; and neglecting population dynamics. I show how correcting these mistakes pushes the value of existential risk mitigation substantially below leading estimates, potentially low enough to…