• Corpus ID: 14213233

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

@inproceedings{Marcolino2011LeandroSM,
  title={Leandro Soriano Marcolino Advisor : Hitoshi Matsubara Multi-Agent Monte Carlo Go},
  author={Leandro Soriano Marcolino and Hitoshi Matsubara and Carlo Go},
  year={2011}
}
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… 

References

SHOWING 1-10 OF 57 REFERENCES
Finite-time Analysis of the Multiarmed Bandit Problem
TLDR
This work shows that the optimal logarithmic regret is also achievable uniformly over time, with simple and efficient policies, and for all reward distributions with bounded support.
Multi-agent Monte Carlo Go
TLDR
A Multi-Agent version of UCT Monte Carlo Go is proposed, using the emergent behavior of a great number of simple agents to increase the quality of the Monte Carlo simulations, increasing the strength of the artificial player as a whole.
Computer Go: An AI oriented survey
Mathematical games: the fantastic combinations of john conway's new solitaire game "life
TLDR
In 1967 he discovered a new group-some call it "Conway's constellation"--that includes all but two of the then known sporadic groups, a breakthrough that has had exciting repercussions in both group theory and number theory.
Forward Pruning and Other Heuristic Search Techniques in Tsume Go
Computer go as a sum of local games: an application of combinatorial game theory
TLDR
This thesis claims that combinatorial game theory can be applied to computer Go, and develops a sum game model for heuristic Go programming and a program for perfect play in late stage endgames as a case study in Knowledge Engineering.
Modification of UCT with Patterns in Monte-Carlo Go
TLDR
A Monte-Carlo Go program, MoGo, which is the first computer Go program using UCT, is developed, and the modification of UCT for Go application is explained and also the intelligent random simulation with patterns which has improved significantly the performance of MoGo.
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
TLDR
This novel parallel Monte-Carlo tree search algorithm can run on a loosely coupled heterogeneous computer cluster, consists of inexpensive personal computers and game consoles, on a moderate speed network and allows users to connect or disconnect the servers on-the-fly, in contrast to ones run on an expensive HPC cluster.
A model of visual organization for the game of GO
TLDR
A program which plays GO uses an information processing model to produce perceptual features which are seen by human GO players, and is capable of several responses to the recognition of significant configurations of these perceptual features.
Flocks, herds and schools: A distributed behavioral model
TLDR
This paper explores an approach based on simulation as an alternative to scripting the paths of each bird individually, an elaboration of a particle systems, with the simulated birds being the particles.
...
...