A Game-Theoretic Analysis of the Off-Switch Game
Computer Science and Game Theory
2017-08-15 v1
Abstract
The off-switch game is a game theoretic model of a highly intelligent robot interacting with a human. In the original paper by Hadfield-Menell et al. (2016), the analysis is not fully game-theoretic as the human is modelled as an irrational player, and the robot's best action is only calculated under unrealistic normality and soft-max assumptions. In this paper, we make the analysis fully game theoretic, by modelling the human as a rational player with a random utility function. As a consequence, we are able to easily calculate the robot's best action for arbitrary belief and irrationality assumptions.
Cite
@article{arxiv.1708.03871,
title = {A Game-Theoretic Analysis of the Off-Switch Game},
author = {Tobias Wängberg and Mikael Böörs and Elliot Catt and Tom Everitt and Marcus Hutter},
journal= {arXiv preprint arXiv:1708.03871},
year = {2017}
}