BTT-Go: An Agent for Go that Uses a Transposition Table to Reduce the Simulations and the Supervision in the Monte-Carlo Tree Search

This paper presents BTT-Go: an agent for Go whose architecture is based on the well-known agent Fuego, that is, its search process for the best move is based on simulations of games performed by means of MonteCarlo Tree Search (MCTS). In Fuego, these simulations are guided by supervised heuristics called prior knowledge and play-out policy. In this context, the goal behind the BTT-Go proposal is to reduce the supervised character of Fuego, granting it more autonomy. To cope with this task, the BTT-Go counts on a Transposition Table (TT) whose role is not to waste the history of the nodes that have already been explored throughout the game. By this way, the agent proposed here reduces the supervised character of Fuego by replacing, whenever possible, the prior knowledge and the play-out policy with the information retrieved from the TT. Several evaluative tournaments involving BTT-Go and Fuego confirm that the former obtains satisfactory results in its purpose of attenuating the supervision in Fuego without losing its competitiveness, even in 19x19 game-boards.