“A Game-Theoretic Analysis of the Off-Switch Game”, 2017-08-13 (; similar):
The off-switch game is a game theoretic model of a highly intelligent robot interacting with a human.
In the original paper by Hadfield- et al 2016, the analysis is not fully game-theoretic as the human is modeled 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 modeling 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.