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
When should an effective altruist donate? – William MacAskill (Global Priorities Institute, Oxford University)
Effective altruism is the use of evidence and careful reasoning to work out how to maximize positive impact on others with a given unit of resources, and the taking of action on that basis. It’s a philosophy and a social movement that is gaining considerable steam in the philanthropic world. For example,…
Consciousness makes things matter – Andrew Y. Lee (University of Toronto)
This paper argues that phenomenal consciousness is what makes an entity a welfare subject, or the kind of thing that can be better or worse off. I develop and motivate this view, and then defend it from objections concerning death, non-conscious entities that have interests (such as plants), and conscious subjects that necessarily have welfare level zero. I also explain how my theory of welfare subjects relates to experientialist and anti-experientialist theories of welfare goods.
Respect for others’ risk attitudes and the long-run future – Andreas Mogensen (Global Priorities Institute, University of Oxford)
When our choice affects some other person and the outcome is unknown, it has been argued that we should defer to their risk attitude, if known, or else default to use of a risk avoidant risk function. This, in turn, has been claimed to require the use of a risk avoidant risk function when making decisions that primarily affect future people, and to decrease the desirability of efforts to prevent human extinction, owing to the significant risks associated with continued human survival. …