English

Monte Carlo Action Programming

Artificial Intelligence 2017-03-01 v1 Programming Languages

Abstract

This paper proposes Monte Carlo Action Programming, a programming language framework for autonomous systems that act in large probabilistic state spaces with high branching factors. It comprises formal syntax and semantics of a nondeterministic action programming language. The language is interpreted stochastically via Monte Carlo Tree Search. Effectiveness of the approach is shown empirically.

Keywords

Cite

@article{arxiv.1702.08441,
  title  = {Monte Carlo Action Programming},
  author = {Lenz Belzner},
  journal= {arXiv preprint arXiv:1702.08441},
  year   = {2017}
}