On the Computability of AIXI
Abstract
How could we solve the machine learning and the artificial intelligence problem if we had infinite computation? Solomonoff induction and the reinforcement learning agent AIXI are proposed answers to this question. Both are known to be incomputable. In this paper, we quantify this using the arithmetical hierarchy, and prove upper and corresponding lower bounds for incomputability. We show that AIXI is not limit computable, thus it cannot be approximated using finite computation. Our main result is a limitcomputable {\epsilon}optimal version of AIXI with infinite horizon that maximizes expected rewards.
 Publication:

arXiv eprints
 Pub Date:
 October 2015
 arXiv:
 arXiv:1510.05572
 Bibcode:
 2015arXiv151005572L
 Keywords:

 Computer Science  Artificial Intelligence
 EPrint:
 UAI 2015