Massively Parallel Monte Carlo Tree Search
Kamil Rocki (The University of Tokyo)
Reiji Suda (The University of Tokyo)
Monte Carlo Tree Search is a method of finding near-optimal solutions for large state-space problems. Currently, is it very important to develop algorithms being able to take advantage of great number of processors in such areas. In this paper MCTS parallel implementations for thousand of cores are presented and discussed. The MCTS parallelization method used is the root parallelization. Implementation of the distributed scheme uses MPI. Results presented are based on the Reversi game rules.
Parallel and Distributed Computing, Performance Analysis