Towards shutdownable agents via stochastic choice
Elliott Thornley (Global Priorities Institute, University of Oxford), Alexander Roman (New College of Florida), Christos Ziakas (Imperial College, London), Leyton Ho (Brown University) and Louis Thomson (University of Oxford)
GPI Working Paper No. 16-2024
The Incomplete Preferences Proposal (IPP) is an idea for ensuring that advanced artificial agents never resist shutdown. 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 provide some initial evidence that DReST reward functions could train advanced agents to be USEFUL and NEUTRAL. Our theoretical work suggests that these agents would be useful and shutdownable.
Other working papers
Strong longtermism and the challenge from anti-aggregative moral views – Karri Heikkinen (University College London)
Greaves and MacAskill (2019) argue for strong longtermism, according to which, in a wide class of decision situations, the option that is ex ante best, and the one we ex ante ought to choose, is the option that makes the very long-run future go best. One important aspect of their argument is the claim that strong longtermism is compatible with a wide range of ethical assumptions, including plausible non-consequentialist views. In this essay, I challenge this claim…
Maximal cluelessness – Andreas Mogensen (Global Priorities Institute, Oxford University)
I argue that many of the priority rankings that have been proposed by effective altruists seem to be in tension with apparently reasonable assumptions about the rational pursuit of our aims in the face of uncertainty. The particular issue on which I focus arises from recognition of the overwhelming importance…
Time discounting, consistency and special obligations: a defence of Robust Temporalism – Harry R. Lloyd (Yale University)
This paper defends the claim that mere temporal proximity always and without exception strengthens certain moral duties, including the duty to save – call this view Robust Temporalism. Although almost all other moral philosophers dismiss Robust Temporalism out of hand, I argue that it is prima facie intuitively plausible, and that it is analogous to a view about special obligations that many philosophers already accept…