Title
More Trees or Larger Trees: Parallelizing Monte Carlo Tree Search
Abstract
Monte Carlo tree search (MCTS) is being effectively used in many domains, but acquiring good results from building larger trees takes time that can in many cases be impractical. In this article, we show that parallelizing the tree building process using multiple independent trees (root parallelization) can improve results when limited time is available, and compare these results to other paralleli...
Year
DOI
Venue
2021
10.1109/TG.2020.3048331
IEEE Transactions on Games
Keywords
DocType
Volume
Games,Monte Carlo methods,Buildings,Training,Instruction sets,Backpropagation,Testing
Journal
13
Issue
ISSN
Citations 
3
2475-1502
0
PageRank 
References 
Authors
0.34
0
2
Name
Order
Citations
PageRank
Erik S. Steinmetz1195.10
Maria L. Gini232.23