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
Estimating long-term treatment effects without long-term outcome data – David Rhys Bernard (Rethink Priorities), Jojo Lee and Victor Yaneng Wang (Global Priorities Institute, University of Oxford)
The surrogate index method allows policymakers to estimate long-run treatment effects before long-run outcomes are observable. We meta-analyse this approach over nine long-run RCTs in development economics, comparing surrogate estimates to estimates from actual long-run RCT outcomes. We introduce the M-lasso algorithm for constructing the surrogate approach’s first-stage predictive model and compare its performance with other surrogate estimation methods. …
Minimal and Expansive Longtermism – Hilary Greaves (University of Oxford) and Christian Tarsney (Population Wellbeing Initiative, University of Texas at Austin)
The standard case for longtermism focuses on a small set of risks to the far future, and argues that in a small set of choice situations, the present marginal value of mitigating those risks is very great. But many longtermists are attracted to, and many critics of longtermism worried by, a farther-reaching form of longtermism. According to this farther-reaching form, there are many ways of improving the far future, which determine the value of our options in all or nearly all choice situations…
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…