Optimisation of MCTS Player for The Lord of the Rings: The Card Game

TL;DR

This paper enhances Monte-Carlo Tree Search (MCTS) for an AI player in 'The Lord of the Rings' card game by integrating expert knowledge and multi-stage decision strategies, improving performance as game complexity rises.

Contribution

It introduces a novel hybrid approach combining expert knowledge with MCTS at various decision stages for complex card games.

Findings

Hybrid MCTS with expert knowledge outperforms pure MCTS.

Replacing random playouts with expert-informed playouts improves success rates.

Effectiveness increases with game difficulty.

Abstract

The article presents research on the use of Monte-Carlo Tree Search (MCTS) methods to create an artificial player for the popular card game "The Lord of the Rings". The game is characterized by complicated rules, multi-stage round construction, and a high level of randomness. The described study found that the best probability of a win is received for a strategy combining expert knowledge-based agents with MCTS agents at different decision stages. It is also beneficial to replace random playouts with playouts using expert knowledge. The results of the final experiments indicate that the relative effectiveness of the developed solution grows as the difficulty of the game increases.