Corpus ID: 14213233

Leandro Soriano Marcolino Advisor : Hitoshi Matsubara Multi-Agent Monte Carlo Go

  title={Leandro Soriano Marcolino Advisor : Hitoshi Matsubara Multi-Agent Monte Carlo Go},
  author={Leandro Soriano Marcolino and Hitoshi Matsubara and C. Go},
Go is a strategic board game that is considered one of the greatest challenges for Arti cial Intelligence. Many algorithms have been proposed, trying to tackle this problem, but generally all of them generated players that could be easily defeated by a strong human opponent. UCT Monte Carlo Go is one of the most successful algorithms. The basic idea is to associate a tree search with pseudo-random simulations, used to evaluate the leaves. Nowadays, the literature is more focused on how to… CONTINUE READING


Finite-time Analysis of the Multiarmed Bandit Problem
  • 4,412
  • PDF
Multi-agent Monte Carlo Go
  • 17
  • PDF
Computer Go: An AI oriented survey
  • 231
  • PDF
Mathematical games: the fantastic combinations of john conway's new solitaire game "life
  • 1,397
  • PDF
Forward Pruning and Other Heuristic Search Techniques in Tsume Go
  • 38
Computer go as a sum of local games: an application of combinatorial game theory
  • 66
Modification of UCT with Patterns in Monte-Carlo Go
  • 358
  • PDF
Parallel Monte-Carlo Tree Search with Simulation Servers
  • H. Kato, I. Takeuchi
  • Computer Science
  • 2010 International Conference on Technologies and Applications of Artificial Intelligence
  • 2010
  • 32
A model of visual organization for the game of GO
  • 49
  • PDF
Flocks, herds and schools: A distributed behavioral model
  • 5,230
  • PDF