English

On the Computability of Solomonoff Induction and Knowledge-Seeking

Artificial Intelligence 2015-10-20 v1 Machine Learning

Abstract

Solomonoff induction is held as a gold standard for learning, but it is known to be incomputable. We quantify its incomputability by placing various flavors of Solomonoff's prior M in the arithmetical hierarchy. We also derive computability bounds for knowledge-seeking agents, and give a limit-computable weakly asymptotically optimal reinforcement learning agent.

Keywords

Cite

@article{arxiv.1507.04124,
  title  = {On the Computability of Solomonoff Induction and Knowledge-Seeking},
  author = {Jan Leike and Marcus Hutter},
  journal= {arXiv preprint arXiv:1507.04124},
  year   = {2015}
}

Comments

ALT 2015

R2 v1 2026-06-22T10:12:10.098Z