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

PDF download

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

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. …

Numbers Tell, Words Sell – Michael Thaler (University College London), Mattie Toma (University of Warwick) and Victor Yaneng Wang (Massachusetts Institute of Technology)

When communicating numeric estimates with policymakers, journalists, or the general public, experts must choose between using numbers or natural language. We run two experiments to study whether experts strategically use language to communicate numeric estimates in order to persuade receivers. In Study 1, senders communicate probabilities of abstract events to receivers on Prolific, and in Study 2 academic researchers communicate the effect sizes in research papers to government policymakers. When…

Crying wolf: Warning about societal risks can be reputationally risky – Lucius Caviola (Global Priorities Institute, University of Oxford) et al.

Society relies on expert warnings about large-scale risks like pandemics and natural disasters. Across ten studies (N = 5,342), we demonstrate people’s reluctance to warn about unlikely but large-scale risks because they are concerned about being blamed for being wrong. In particular, warners anticipate that if the risk doesn’t occur, they will be perceived as overly alarmist and responsible for wasting societal resources. This phenomenon appears in the context of natural, technological, and financial risks…