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 does not 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
Consequentialism, Cluelessness, Clumsiness, and Counterfactuals – Alan Hájek (Australian National University)
According to a standard statement of objective consequentialism, a morally right action is one that has the best consequences. More generally, given a choice between two actions, one is morally better than the other just in case the consequences of the former action are better than those of the latter. (These are not just the immediate consequences of the actions, but the long-term consequences, perhaps until the end of history.) This account glides easily off the tongue—so easily that…
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…
The unexpected value of the future – Hayden Wilkinson (Global Priorities Institute, University of Oxford)
Various philosophers accept moral views that are impartial, additive, and risk-neutral with respect to betterness. But, if that risk neutrality is spelt out according to expected value theory alone, such views face a dire reductio ad absurdum. If the expected sum of value in humanity’s future is undefined—if, e.g., the probability distribution over possible values of the future resembles the Pasadena game, or a Cauchy distribution—then those views say that no real-world option is ever better than any other. And, as I argue…