Year: 2015
Type: preprint
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 limit-computable ε-optimal version of AIXI with infinite horizon that maximizes expected rewards.
Source: arXiv (Cornell University)
Authors: Leike, Jan, Hutter, Marcus
Institution: Australian National University
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W1773344762