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
The freedom of future people – Andreas T Schmidt (University of Groningen)
What happens to liberal political philosophy, if we consider not only the freedom of present but also future people? In this article, I explore the case for long-term liberalism: freedom should be a central goal, and we should often be particularly concerned with effects on long-term future distributions of freedom. I provide three arguments. First, liberals should be long-term liberals: liberal arguments to value freedom give us reason to be (particularly) concerned with future freedom…
The weight of suffering – Andreas Mogensen (Global Priorities Institute, University of Oxford)
How should we weigh suffering against happiness? This paper highlights the existence of an argument from intuitively plausible axiological principles to the striking conclusion that in comparing different populations, there exists some depth of suffering that cannot be compensated for by any measure of well-being. In addition to a number of structural principles, the argument relies on two key premises. The first is the contrary of the so-called Reverse Repugnant Conclusion…
Against Anti-Fanaticism – Christian Tarsney (Population Wellbeing Initiative, University of Texas at Austin)
Should you be willing to forego any sure good for a tiny probability of a vastly greater good? Fanatics say you should, anti-fanatics say you should not. Anti-fanaticism has great intuitive appeal. But, I argue, these intuitions are untenable, because satisfying them in their full generality is incompatible with three very plausible principles: acyclicity, a minimal dominance principle, and the principle that any outcome can be made better or worse. This argument against anti-fanaticism can be…