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
Existential risks from a Thomist Christian perspective – Stefan Riedener (University of Zurich)
Let’s say with Nick Bostrom that an ‘existential risk’ (or ‘x-risk’) is a risk that ‘threatens the premature extinction of Earth-originating intelligent life or the permanent and drastic destruction of its potential for desirable future development’ (2013, 15). There are a number of such risks: nuclear wars, developments in biotechnology or artificial intelligence, climate change, pandemics, supervolcanos, asteroids, and so on (see e.g. Bostrom and Ćirković 2008). …
Ethical Consumerism – Philip Trammell (Global Priorities Institute and Department of Economics, University of Oxford)
I study a static production economy in which consumers have not only preferences over their own consumption but also external, or “ethical”, preferences over the supply of each good. Though existing work on the implications of external preferences assumes price-taking, I show that ethical consumers generically prefer not to act even approximately as price-takers. I therefore introduce a near-Nash equilibrium concept that generalizes the near-Nash equilibria found in literature on strategic foundations of general equilibrium…
Altruism in governance: Insights from randomized training – Sultan Mehmood, (New Economic School), Shaheen Naseer (Lahore School of Economics) and Daniel L. Chen (Toulouse School of Economics)
Randomizing different schools of thought in training altruism finds that training junior deputy ministers in the utility of empathy renders at least a 0.4 standard deviation increase in altruism. Treated ministers increased their perspective-taking: blood donations doubled, but only when blood banks requested their exact blood type. Perspective-taking in strategic dilemmas improved. Field measures such as orphanage visits and volunteering in impoverished schools also increased, as did their test scores in teamwork assessments…