Student Work

Monte-Carlo Search Algorithms

Público

Conteúdo disponível para baixar

open in viewer

We have explored and tested the behavior of Monte-Carlo Search Algorithms in both artificial and real game trees. Complementing the work of previous WPI students, we have expanded the Gomba Testing Framework; a platform for the comparative evaluation of search algorithms in large adversarial game trees. We implemented and analyzed the specific UCT algorithm PoolRAVE by developing and testing variations of it in an existing framework of Go algorithms. We have implemented these algorithm variations in computer Go and verified their relative performances against established algorithms.

  • This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.
Creator
Publisher
Identifier
  • E-project-042811-032006
Advisor
Year
  • 2011
Center
Sponsor
Date created
  • 2011-04-28
Localização
  • Budapest
Resource type
Major
Rights statement

Relações

Em Collection:

Itens

Itens

Permanent link to this page: https://digital.wpi.edu/show/n870zs243