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 Incomplete Preferences Proposal (IPP) is an idea for ensuring that advanced artificial agents never resist shutdown. 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 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
A Fission Problem for Person-Affecting Views – Elliott Thornley (Global Priorities Institute, University of Oxford)
On person-affecting views in population ethics, the moral import of a person’s welfare depends on that person’s temporal or modal status. These views typically imply that – all else equal – we’re never required to create extra people, or to act in ways that increase the probability of extra people coming into existence. In this paper, I use Parfit-style fission cases to construct a dilemma for person-affecting views: either they forfeit their seeming-advantages and face fission analogues…
How to neglect the long term – Hayden Wilkinson (Global Priorities Institute, University of Oxford)
Consider longtermism: the view that, at least in some of the most important decisions facing agents today, which options are morally best is determined by which are best for the long-term future. Various critics have argued that longtermism is false—indeed, that it is obviously false, and that we can reject it on normative grounds without close consideration of certain descriptive facts. In effect, it is argued, longtermism would be false even if real-world agents had promising means…
Future Suffering and the Non-Identity Problem – Theron Pummer (University of St Andrews)
I present and explore a new version of the Person-Affecting View, according to which reasons to do an act depend wholly on what would be said for or against this act from the points of view of particular individuals. According to my view, (i) there is a morally requiring reason not to bring about lives insofar as they contain suffering (negative welfare), (ii) there is no morally requiring reason to bring about lives insofar as they contain happiness (positive welfare), but (iii) there is a permitting reason to bring about lives insofar as they…