Bulletin of the Polish Academy of Sciences: Technical Sciences

Abstract

they are an effective, modern educational tool [13], e.g., in medicine [14]. Cooperation allows to learn teamwork, and this is often not possible without the additional presence of artificial players with decision making skills. The main difficulty in cooperative games is created by a complex, multi-stage round structure, which contains several unpredictable random events. Cooperative games make it also possible to play solo, which was analysed in this research.An interesting approach for MCTS application in collectible card games has been presented in 2019 using the "Hearthstone" game [15]. Authors identified huge size of the action space. Several precautions had been taken to reduce number of allowed moves. Using Action filtering and Obliged Actions are examples of successful domain-specific knowledge incorporation.This article is directly based on authors conference work [16]. The algorithm has been extended by adding more expert knowledge into the standard MCTS implementation. This allowed to perform a new analysis for games with high complexity level. We have demonstrated that the relative effectiveness of the mixed strategy proposed in [16] rises as the difficulty of the problem increases. The Lord of the Rings: The Card Game"The Lord of the Rings: The Card Game", often abbreviated as LoTR, is a complicated cooperative card game with several decision-making stages. The following section is devoted to the presentation of its basic rules. It is necessary to understand before we will discuss construction of the game simulator, and searching for the optimal strategy for the AI player. Living Card Game.From the Poker to the "Magic: the Gathering", card games belong to a group of games characterized by hidden information and a high degree of randomness. Hidden information means that the player does not have a complete view of the game, opposing cards