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
Doomsday and objective chance – Teruji Thomas (Global Priorities Institute, Oxford University)
Lewis’s Principal Principle says that one should usually align one’s credences with the known chances. In this paper I develop a version of the Principal Principle that deals well with some exceptional cases related to the distinction between metaphysical and epistemic modality. I explain how this principle gives a unified account of the Sleeping Beauty problem and chance-based principles of anthropic reasoning…
Philosophical considerations relevant to valuing continued human survival: Conceptual Analysis, Population Axiology, and Decision Theory – Andreas Mogensen (Global Priorities Institute, University of Oxford)
Many think that human extinction would be a catastrophic tragedy, and that we ought to do more to reduce extinction risk. There is less agreement on exactly why. If some catastrophe were to kill everyone, that would obviously be horrific. Still, many think the deaths of billions of people don’t exhaust what would be so terrible about extinction. After all, we can be confident that billions of people are going to die – many horribly and before their time – if humanity does not go extinct. …
What power-seeking theorems do not show – David Thorstad (Vanderbilt University)
Recent years have seen increasing concern that artificial intelligence may soon pose an existential risk to humanity. One leading ground for concern is that artificial agents may be power-seeking, aiming to acquire power and in the process disempowering humanity. A range of power-seeking theorems seek to give formal articulation to the idea that artificial agents are likely to be power-seeking. I argue that leading theorems face five challenges, then draw lessons from this result.