A novel ontology for computer go knowledge management

Lee, Chang-Shing; Wang, Mei-Hui; Hong, Tzung-Pei; Chaslot, Guillaume; Hoock, Jean‐Baptiste; Rimmel, Arpad; Teytaud, Olivier; Kuo, Yau‐Hwang

doi:10.1109/fuzzy.2009.5277222

Cited by 10 publications

(3 citation statements)

References 19 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since then, progress has been rapid, with the program MOGO beating a professional player on a 9 × 9 board in 2008 [128] and on a large board (with a large handicap) also in 2008. This success is also summarised in [129]. Today, the top computer Go programs all use MCTS and play at the strength of a good amateur player.…”

Section: Gomentioning

confidence: 96%

A Survey of Monte Carlo Tree Search Methods

Browne

Powley

Whitehouse

et al. 2012

IEEE Trans. Comput. Intell. AI Games

2,329

1,535

View full text Add to dashboard Cite

Monte Carlo Tree Search (MCTS) is a recently proposed search method that combines the precision of tree search with the generality of random sampling. It has received considerable interest due to its spectacular success in the difficult problem of computer Go, but has also proved beneficial in a range of other domains. This paper is a survey of the literature to date, intended to provide a snapshot of the state of the art after the first five years of MCTS research. We outline the core algorithm's derivation, impart some structure on the many variations and enhancements that have been proposed, and summarise the results from the key game and non-game domains to which MCTS methods have been applied. A number of open research questions indicate that the field is ripe for future work.

show abstract

Section: Gomentioning

confidence: 96%

A Survey of Monte Carlo Tree Search Methods

Browne

Powley

Whitehouse

et al. 2012

IEEE Trans. Comput. Intell. AI Games

2,329

1,535

View full text Add to dashboard Cite

show abstract

“…Because of the huge success of Monte Carlo methods, both programs also incorporate these techniques. Lee et al (2009) developed a very successful Go program called MoGo combining Monte Carlo tree search evaluation, moves extracted from databases, and an expert rule system [2]. There have also been several approaches using Artificial Neural Networks (ANNs) to either assess the current board situation or to choose the next move directly.…”

Section: Related Workmentioning

confidence: 99%

Evolution of a digital organism playing Go

Alt

Mayer

2013

2013 IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS)

View full text Add to dashboard Cite

Digital organisms (DOs) model the basic structure and development of natural organisms to create robust, scalable, and adaptive solutions to problems from different fields. The applicability of DOs has been investigated mainly on a few synthetic problems like pattern creation, but on a very limited number of real world problems, e.g., the creation of architectural structures. In this paper the potential of DOs for learning to play the game of Go is demonstrated. Go has been chosen for its high complexity, its simple set of rules, and its pattern-oriented structure. A DO is designed, which is able to learn to play the game of Go by means of artificial evolution. The DO is evolved against three computer opponents of different strength on a 5 × 5 board. Specifically, we are interested in the DO's scalability, when evolved to play on the small board and transferred to a larger board without any external adaptations.

show abstract

“…Crazy Stone demonstrated almost perfect play. Since 2008, National University of Tainan (NUTN) in Taiwan and other academic organizations have hosted or organized several human vs. computer Go-related events, including the 2008 Computational Intelligence Forum & World 9u 9 Computer Go Championship [8], and 2009 Invited Games for MoGo vs. Taiwan Professional Go Players (Taiwan Open 2009)[9]. Besides, the FUZZ-IEEE 2009: Panel, Invited Sessions, and Human vs. Computer Go Competition[10] was held at the 2009 International Conference on Fuzzy Systems in Aug. 2009.…”

mentioning

confidence: 99%

Panel sessions

2011

2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011)

View full text Add to dashboard Cite

A novel ontology for computer go knowledge management

Cited by 10 publications

References 19 publications

A Survey of Monte Carlo Tree Search Methods

A Survey of Monte Carlo Tree Search Methods

Evolution of a digital organism playing Go

Panel sessions

Contact Info

Product

Resources

About