Towards shutdownable agents via stochastic choice
Elliott Thornley (Global Priorities Institute, University of Oxford), Alexander Roman (New College of Florida), Christos Ziakas (Imperial College, London), Leyton Ho (Brown University) and Louis Thomson (University of Oxford)
GPI Working Paper No. 16-2024
The POST-Agents Proposal (PAP) is an idea for ensuring that advanced artificial agents never resist shutdown. A key part of the PAP 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 provide some initial evidence that DReST reward functions could train advanced agents to be USEFUL and NEUTRAL. Our theoretical work suggests that these agents would be useful and shutdownable.
Other working papers
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…
The Shutdown Problem: An AI Engineering Puzzle for Decision Theorists – Elliott Thornley (Global Priorities Institute, University of Oxford)
I explain and motivate the shutdown problem: the problem of designing artificial agents that (1) shut down when a shutdown button is pressed, (2) don’t try to prevent or cause the pressing of the shutdown button, and (3) otherwise pursue goals competently. I prove three theorems that make the difficulty precise. These theorems suggest that agents satisfying some innocuous-seeming conditions will often try to prevent or cause the pressing of the shutdown button, even in cases where it’s costly to do so. I end by noting that…
Concepts of existential catastrophe – Hilary Greaves (University of Oxford)
The notion of existential catastrophe is increasingly appealed to in discussion of risk management around emerging technologies, but it is not completely clear what this notion amounts to. Here, I provide an opinionated survey of the space of plausibly useful definitions of existential catastrophe. Inter alia, I discuss: whether to define existential catastrophe in ex post or ex ante terms, whether an ex ante definition should be in terms of loss of expected value or loss of potential…