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
Cassandra’s Curse: A second tragedy of the commons – Philippe Colo (ETH Zurich)
This paper studies why scientific forecasts regarding exceptional or rare events generally fail to trigger adequate public response. I consider a game of contribution to a public bad. Prior to the game, I assume contributors receive non-verifiable expert advice regarding uncertain damages. In addition, I assume that the expert cares only about social welfare. Under mild assumptions, I show that no information transmission can happen at equilibrium when the number of contributors…
Population ethical intuitions – Lucius Caviola (Harvard University) et al.
Is humanity’s existence worthwhile? If so, where should the human species be headed in the future? In part, the answers to these questions require us to morally evaluate the (potential) human population in terms of its size and aggregate welfare. This assessment lies at the heart of population ethics. Our investigation across nine experiments (N = 5776) aimed to answer three questions about how people aggregate welfare across individuals: (1) Do they weigh happiness and suffering symmetrically…
Heuristics for clueless agents: how to get away with ignoring what matters most in ordinary decision-making – David Thorstad and Andreas Mogensen (Global Priorities Institute, Oxford University)
Even our most mundane decisions have the potential to significantly impact the long-term future, but we are often clueless about what this impact may be. In this paper, we aim to characterize and solve two problems raised by recent discussions of cluelessness, which we term the Problems of Decision Paralysis and the Problem of Decision-Making Demandingness. After reviewing and rejecting existing solutions to both problems, we argue that the way forward is to be found in the distinction between procedural and substantive rationality…