English

Universal Sequential Decisions in Unknown Environments

Artificial Intelligence 2007-05-23 v2 Computational Complexity Machine Learning

Abstract

We give a brief introduction to the AIXI model, which unifies and overcomes the limitations of sequential decision theory and universal Solomonoff induction. While the former theory is suited for active agents in known environments, the latter is suited for passive prediction of unknown environments.

Cite

@article{arxiv.cs/0306091,
  title  = {Universal Sequential Decisions in Unknown Environments},
  author = {Marcus Hutter},
  journal= {arXiv preprint arXiv:cs/0306091},
  year   = {2007}
}

Comments

2 pages