Batch Monte Carlo Tree Search
This work addresses efficiency in game-playing AI for Go, but it is incremental as it builds on existing MCTS methods with optimizations.
The authors tackled the problem of accelerating Monte Carlo Tree Search (MCTS) by using batched GPU inferences and combining search trees with transposition tables, resulting in improved performance evaluated in the game of Go with a MobileNet neural network.
Making inferences with a deep neural network on a batch of states is much faster with a GPU than making inferences on one state after another. We build on this property to propose Monte Carlo Tree Search algorithms using batched inferences. Instead of using either a search tree or a transposition table we propose to use both in the same algorithm. The transposition table contains the results of the inferences while the search tree contains the statistics of Monte Carlo Tree Search. We also propose to analyze multiple heuristics that improve the search: the $μ$ FPU, the Virtual Mean, the Last Iteration and the Second Move heuristics. They are evaluated for the game of Go using a MobileNet neural network.