2017/04/02 by S. Ali Mirsoleimani, Mirsoleimani, S. Ali, Aske Plaat +7
Computer Science · #Algorithms and Data Compression #Artificial Intelligence (cs.AI) #Artificial Intelligence in Games #FOS: Computer and information sciences #Parallel Computing and Optimization Techniques #cs.AI
paper · pdf · doi:10.48550/arxiv.1704.00325
9 pages
arxiv created 2017/04/02 · openalex publication_date 2017/04/02 · arxiv updated 2017/04/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
In this paper, we present a new algorithm for parallel Monte Carlo tree search (MCTS). It is based on the pipeline pattern and allows flexible management of the control flow of the operations in parallel MCTS. The pipeline pattern provides for the first structured parallel programming approach to MCTS. Moreover, we propose a new lock-free tree data structure for parallel MCTS which removes synchronization overhead. The Pipeline Pattern for Parallel MCTS algorithm (called 3PMCTS), scales very well to higher numbers of cores when compared to the existing methods.