English

Death and Suicide in Universal Artificial Intelligence

Artificial Intelligence 2016-06-03 v1

Abstract

Reinforcement learning (RL) is a general paradigm for studying intelligent behaviour, with applications ranging from artificial intelligence to psychology and economics. AIXI is a universal solution to the RL problem; it can learn any computable environment. A technical subtlety of AIXI is that it is defined using a mixture over semimeasures that need not sum to 1, rather than over proper probability measures. In this work we argue that the shortfall of a semimeasure can naturally be interpreted as the agent's estimate of the probability of its death. We formally define death for generally intelligent agents like AIXI, and prove a number of related theorems about their behaviour. Notable discoveries include that agent behaviour can change radically under positive linear transformations of the reward signal (from suicidal to dogmatically self-preserving), and that the agent's posterior belief that it will survive increases over time.

Keywords

Cite

@article{arxiv.1606.00652,
  title  = {Death and Suicide in Universal Artificial Intelligence},
  author = {Jarryd Martin and Tom Everitt and Marcus Hutter},
  journal= {arXiv preprint arXiv:1606.00652},
  year   = {2016}
}

Comments

Conference: Artificial General Intelligence (AGI) 2016 13 pages, 2 figures

R2 v1 2026-06-22T14:15:50.205Z