Current Frontiers in Computer Go

This paper presents the recent technical advances in Monte Carlo tree search (MCTS) for the game of Go, shows the many similarities and the rare differences between the current best programs, and reports the results of the Computer Go event organized at the 2009 IEEE International Conference on Fuzz...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on computational intelligence and AI in games. 2010-12, Vol.2 (4), p.229-238
Main Authors: Rimmel, Arpad, Teytaud, Olivier, Chang-Shing Lee, Shi-Jim Yen, Mei-Hui Wang, Shang-Rong Tsai
Format: Article
Language:English
Subjects:
Algorithm design and analysis
Artificial intelligence
Computer simulation
Conferences
Decision trees
Game of Go
Game theory
Games
Human
Mathematics
Monte Carlo methods
Monte Carlo tree search (MCTS)
Optimization and Control
Players
Studies
upper confidence
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents the recent technical advances in Monte Carlo tree search (MCTS) for the game of Go, shows the many similarities and the rare differences between the current best programs, and reports the results of the Computer Go event organized at the 2009 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE2009), in which four main Go programs played against top level humans. We see that in 9 × 9, computers are very close to the best human level, and can be improved easily for the opening book; whereas in 19 × 19, handicap 7 is not enough for the computers to win against top level professional players, due to some clearly understood (but not solved) weaknesses of the current algorithms. Applications far from the game of Go are also cited. Importantly, the first ever win of a computer against a 9th Dan professional player in 9 × 9 Go occurred in this event.
ISSN:1943-068X
2475-1502
1943-0698
2475-1510
DOI:10.1109/TCIAIG.2010.2098876