@inproceedings{b86f89916ca445d387dbd40a2fb60a09,
title = "Technique analysis and designing of program with UCT algorithm for NoGo",
abstract = "As a typical example of dynamic search algorithm, the UCT algorithm was initially used on the computerized game of GO. This paper briefly introduces the Markov Decision process, the Multi-armed Bandit model, and the Upper-Confidence Bandit formula. It analyzes the source and structure of the UCT algorithm in theory, and proves that the UCT algorithm is suitable for the design of the program of NoGo. According to the characteristics of NoGo, in the paper we improved the algorithm in terms of move generation and data reuse. We also tried to establish an off-line knowledge database for research. With experimental data we have tested and evaluated the above methods. The above algorithm and technology have been successfully used in WTShadows the NoGo game program, which enabled us to have won the champion in national competition.",
keywords = "Dynamic Move Queue, Knowledge Base, MAB Model, Markov Decision Process, NoGo, UCT Algorithm",
author = "Rui Li and Yueqiu Wu and Andi Zhang and Chen Ma and Bo Chen and Shuliang Wang",
year = "2013",
doi = "10.1109/CCDC.2013.6561055",
language = "English",
isbn = "9781467355322",
series = "2013 25th Chinese Control and Decision Conference, CCDC 2013",
pages = "923--928",
booktitle = "2013 25th Chinese Control and Decision Conference, CCDC 2013",
note = "2013 25th Chinese Control and Decision Conference, CCDC 2013 ; Conference date: 25-05-2013 Through 27-05-2013",
}