AIJan 15, 2020
Monte Carlo Game Solver
arXiv:2001.05087v16 citations
AI Analysis
This work addresses the challenge of computational efficiency in game solving, which is incremental as it builds on existing methods like Monte Carlo Tree Search.
The authors tackled the problem of speeding up exact game solvers by developing an algorithm that uses online learning of playout policies and Monte Carlo Tree Search to order moves, resulting in greatly improved solving times for multiple games.
We present a general algorithm to order moves so as to speedup exact game solvers. It uses online learning of playout policies and Monte Carlo Tree Search. The learned policy and the information in the Monte Carlo tree are used to order moves in game solvers. They improve greatly the solving time for multiple games.