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
Against Anti-Fanaticism – Christian Tarsney (Population Wellbeing Initiative, University of Texas at Austin)
Should you be willing to forego any sure good for a tiny probability of a vastly greater good? Fanatics say you should, anti-fanatics say you should not. Anti-fanaticism has great intuitive appeal. But, I argue, these intuitions are untenable, because satisfying them in their full generality is incompatible with three very plausible principles: acyclicity, a minimal dominance principle, and the principle that any outcome can be made better or worse. This argument against anti-fanaticism can be…
How much should governments pay to prevent catastrophes? Longtermism’s limited role – Carl Shulman (Advisor, Open Philanthropy) and Elliott Thornley (Global Priorities Institute, University of Oxford)
Longtermists have argued that humanity should significantly increase its efforts to prevent catastrophes like nuclear wars, pandemics, and AI disasters. But one prominent longtermist argument overshoots this conclusion: the argument also implies that humanity should reduce the risk of existential catastrophe even at extreme cost to the present generation. This overshoot means that democratic governments cannot use the longtermist argument to guide their catastrophe policy. …
Calibration dilemmas in the ethics of distribution – Jacob M. Nebel (University of Southern California) and H. Orri Stefánsson (Stockholm University and Swedish Collegium for Advanced Study)
This paper presents a new kind of problem in the ethics of distribution. The problem takes the form of several “calibration dilemmas,” in which intuitively reasonable aversion to small-stakes inequalities requires leading theories of distribution to recommend intuitively unreasonable aversion to large-stakes inequalities—e.g., inequalities in which half the population would gain an arbitrarily large quantity of well-being or resources…