Curling is one of the most strategic winter sports. Recently, many computer scientists have studied curling strategies. The Digital Curling system is a framework used to compare curling strategies. Herein, we present a computer agent based on the Monte-Carlo Tree Search (MCTS) for the Digital Curling framework. We implemented a novel action decision method based on MCTS for Markov decision processes with continuous state space. The experimental results show that our search method is effective for agents with a simple simulation policy and agents with a handmade complex one.
%0 Conference Paper
%1 ohto2017curling
%A Ohto, Katsuki
%A Tanaka, Tetsuro
%B ACG
%D 2017
%E Winands, Mark H. M.
%E van den Herik, H. Jaap
%E Kosters, Walter A.
%I Springer
%K Computersimulation Computerspiel Curling Strategie Taktik
%P 151-164
%R 10.1007/978-3-319-71649-7_13
%T A Curling Agent Based on the Monte-Carlo Tree Search Considering the Similarity of the Best Action Among Similar States
%U http://dblp.uni-trier.de/db/conf/acg/acg2017.html#OhtoT17
%V 10664
%X Curling is one of the most strategic winter sports. Recently, many computer scientists have studied curling strategies. The Digital Curling system is a framework used to compare curling strategies. Herein, we present a computer agent based on the Monte-Carlo Tree Search (MCTS) for the Digital Curling framework. We implemented a novel action decision method based on MCTS for Markov decision processes with continuous state space. The experimental results show that our search method is effective for agents with a simple simulation policy and agents with a handmade complex one.
@inproceedings{ohto2017curling,
abstract = {Curling is one of the most strategic winter sports. Recently, many computer scientists have studied curling strategies. The Digital Curling system is a framework used to compare curling strategies. Herein, we present a computer agent based on the Monte-Carlo Tree Search (MCTS) for the Digital Curling framework. We implemented a novel action decision method based on MCTS for Markov decision processes with continuous state space. The experimental results show that our search method is effective for agents with a simple simulation policy and agents with a handmade complex one.},
added-at = {2019-05-17T15:50:38.000+0200},
author = {Ohto, Katsuki and Tanaka, Tetsuro},
biburl = {https://www.bibsonomy.org/bibtex/2602cd0018a70be2fd9afe12f963c33e6/cckonstanz},
booktitle = {ACG},
doi = {10.1007/978-3-319-71649-7_13},
editor = {Winands, Mark H. M. and van den Herik, H. Jaap and Kosters, Walter A.},
interhash = {7350d335835356bd0b3b52f54111da5e},
intrahash = {602cd0018a70be2fd9afe12f963c33e6},
keywords = {Computersimulation Computerspiel Curling Strategie Taktik},
pages = {151-164},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
timestamp = {2019-05-20T10:10:51.000+0200},
title = {A Curling Agent Based on the Monte-Carlo Tree Search Considering the Similarity of the Best Action Among Similar States},
url = {http://dblp.uni-trier.de/db/conf/acg/acg2017.html#OhtoT17},
volume = 10664,
year = 2017
}