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 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
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). …
The scope of longtermism – David Thorstad (Global Priorities Institute, University of Oxford)
Longtermism holds roughly that in many decision situations, the best thing we can do is what is best for the long-term future. The scope question for longtermism asks: how large is the class of decision situations for which longtermism holds? Although longtermism was initially developed to describe the situation of…
A bargaining-theoretic approach to moral uncertainty – Owen Cotton-Barratt (Future of Humanity Institute, Oxford University), Hilary Greaves (Global Priorities Institute, Oxford University)
This paper explores a new approach to the problem of decision under relevant moral uncertainty. We treat the case of an agent making decisions in the face of moral uncertainty on the model of bargaining theory, as if the decision-making process were one of bargaining among different internal parts of the agent, with different parts committed to different moral theories. The resulting approach contrasts interestingly with the extant “maximise expected choiceworthiness”…