Corpus ID: 14003935

On the Computability of AIXI

@article{Leike2015OnTC,
  title={On the Computability of AIXI},
  author={J. Leike and Marcus Hutter},
  journal={ArXiv},
  year={2015},
  volume={abs/1510.05572}
}
  • J. Leike, Marcus Hutter
  • Published 2015
  • Computer Science, Mathematics
  • ArXiv
  • 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 in-computability. We show that AIXI is not limit computable, thus it cannot be approximated using finite computation. Our main result… CONTINUE READING
    On the computability of Solomonoff induction and AIXI
    • 2
    • PDF
    On the Computability of Solomonoff Induction and Knowledge-Seeking
    • 11
    • PDF
    Bad Universal Priors and Notions of Optimality
    • 25
    • PDF
    Nonparametric General Reinforcement Learning
    • 12
    • PDF
    Death and Suicide in Universal Artificial Intelligence
    • 14
    • PDF
    On the Optimality of General Reinforcement Learners

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 27 REFERENCES