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 risk and growth – Leopold Aschenbrenner (Columbia University)
Human activity can create or mitigate risks of catastrophes, such as nuclear war, climate change, pandemics, or artificial intelligence run amok. These could even imperil the survival of human civilization. What is the relationship between economic growth and such existential risks? In a model of directed technical change, with moderate parameters, existential risk follows a Kuznets-style inverted U-shape. …
Longtermism, aggregation, and catastrophic risk – Emma J. Curran (University of Cambridge)
Advocates of longtermism point out that interventions which focus on improving the prospects of people in the very far future will, in expectation, bring about a significant amount of good. Indeed, in expectation, such long-term interventions bring about far more good than their short-term counterparts. As such, longtermists claim we have compelling moral reason to prefer long-term interventions. …
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). …