Monte Carlo Action Programming

Add code
Feb 25, 2017
Lenz Belzner
Figure 1 for Monte Carlo Action Programming
Figure 2 for Monte Carlo Action Programming
Figure 3 for Monte Carlo Action Programming
Figure 4 for Monte Carlo Action Programming

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

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.

View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon