Highly scalable, shared-memory, Monte-Carlo tree search based Blokus Duo Solver on FPGA

Abstract

In this paper we present our hardware architecture on a highly scalable, shared-memory, Monte-Carlo Tree Search (MCTS) based Blokus-Duo solver. In the proposed architecture each MCTS solver module contains a centralized MCTS controller which can also be implemented using soft-cores with a true dual-port access to a shared memory called main memory, and multitude number of MCTS engines each containing several simulation cores. Consequently, this highly flexible architecture guaranties the optimized performance of the solver regardless of the actual FPGA platform used. Our design has been inspired from parallel MCTS algorithms and is potentially capable of obtaining maximum possible parallelism from MCTS algorithm. On the other hand, in our design we combine MCTS with pruning heuristics to increase both the memory and LE utilizations. The results show that our architecture can run up to 50MHz on DE2-115 platform, where each Simulation core requires 11K LEs and MCTS controller requires 10K LEs.

A New Challenge: Approaching Tetris Link with AI

“…The authors are aware of a similar game called Blokus [10]. It is an interesting game as the branching factor is so large (≈32928 for Blokus Duo on a 14x14 board) that specialized FPGA's have been applied to build good AI for it [11], [12]. Although visually similar, the gameplay is completely different, so Blokus strategies or heuristics do not transfer to Tetris Link.…”