A Game-Theoretic Analysis of the Off-Switch Game
Tobias W\"angberg, Mikael B\"o\"ors, Elliot Catt, Tom Everitt, Marcus, Hutter

TL;DR
This paper provides a fully game-theoretic analysis of the off-switch game, modeling the human as a rational player with a random utility function, enabling more accurate calculation of the robot's optimal actions.
Contribution
It advances the off-switch game analysis by incorporating rational human behavior and arbitrary beliefs, improving upon previous models that assumed irrationality and simplified assumptions.
Findings
Allows calculation of robot's best action under rational human model
Handles arbitrary belief and irrationality assumptions
Enhances understanding of human-robot interaction dynamics
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsReinforcement Learning in Robotics · Advanced Bandit Algorithms Research · Bayesian Modeling and Causal Inference
