遊戲人工智慧的研究非常熱門，其中有許多卡牌遊戲的相關研究，像是著名的爐石戰記 (Hearthstone)和魔法風雲 (Magic: the Gathering)。本研究挑選了一款Legends of Code and Magic (LoCM) 卡牌遊戲，LoCM分為選牌與戰鬥兩階段，指定兩位玩家進行對戰，先將對手英雄血量歸零則獲勝。 LoCM在2019年IEEE Congress on Evolutionary Computation (CEC) 和IEEE Conference on Games (COG) 被接受議題研究及舉辦競賽。
本研究只專注於選牌部分，建立一個自動選牌的策略，戰鬥方法則取用COG 2020 第二名及第四名的方法。文中提出三種選牌法，直接評分法、屬性評分法與屬性牌型評分法，並搭配兩種演化演算法。另外，進行個體適應值穩定度分析，探討遊戲場次數量不同帶來的影響，而大量的遊戲會帶來龐大的計算成本，因此，針對遊戲進行平行化處理，大幅減少計算時間。
在傳統的卡牌遊戲中，牌型是組建牌組相當重要的因素，牌型之間存在著相互剋制的關係，選擇對的牌型剋制敵方在遊戲中有非常佔優勢，因此，文中分析不同選牌法的牌型及選牌時帶來的優、缺點。最後，與COG 2020的前六名玩家進行對戰排名。

[1] 魔法風雲會 (Magic: The Gathering) url：https://magic.wizards.com/zh-hant
[2] 爐石戰記 (Hearthstone) url：https://playhearthstone.com/zh-tw/
[3] Legends of Code and Magic url：https://legendsofcodeandmagic.com/
[4] 線上程式遊戲平台 (Coding Game) url：https://www.codingame.com/
[5] LoCM 版本 1.2 url：https://www.codingame.com/contribute/view/162759566f5a132f64b4de78ed637a2f309a
[6] J. H. Holland, Adaptation in Natural and Artificial Systems: An Introductory Aalysis with Aplications to Bology, Cntrol, and Atificial Itelligence, Michigan Press., 1975.
[7] R. Storn, and K. Price, “Differential Evolution – A Simple and Efficient Heuristic for Global Optimization over Continuous Spaces,” Journal of Global Optimization 11, 341–359, 1997.
[8] J. Kowalski, and R. Miernik, “Evolutionary Approach to Collectible Card Game Arena Deckbuilding using Active Genes,” Proceedings of IEEE Congress on Evolutionary Computation, 2020.
[9] R. Miernik, and J. Kowalski, “Evolving Evaluation Functions for Collectible Card Game AI,” 2021.
[10] M. Witkowski, Ł. Klasinski, and W. Meller, “Implementation of Collectible Card Game AI with Opponent Prediction,” Master Thesis, University of Wrocław, 2020.[11] R.Vieira, A. R. Tavares, and L. Chaimowicz, “Drafting in Collectible Card Games via Reinforcement Learning,” 2020 19th Brazilian Symposium on Computer Games and Digital Entertainment, SBGames, pp. 54-61, 2020.
[12] R. Vieira, L. Chaimowicz, and A. R. Tavares, “Reinforcement Learning in Collectible Card Games: Preliminary Results on Legends of Code and Magic,” In 18th Brazilian Symposium on Computer Games and Digital Entertainment, SBGames, pp. 611-614, October 2019.
[13] R. Montoliu, R. D. Gaina, D. Pérez-Liébana, D. Delgado , and S. Lucas, “Efficient Heuristic Policy Optimisation for a Challenging Strategic Card Game,” Proceedings of the International Conference on the Applications of Evolutionary Computation (Part of EvoStar), pp. 403–418, 2020.
[14] S. Lucas , J. Liu, and D. P. Liebana, “The N-Tuple Bandit Evolutionary Algorithm for Game Agent Optimisation.” 2018 IEEE Congress on Evolutionary Computation (CEC), 2018.
[15] P. García-Sánchez, A. Tonda, G. Squillero, A. Mora and J. J. Merelo, “Evolutionary Deckbuilding in Hearthstone,” 2016 IEEE Conference on Computational Intelligence and Games, 2016.
[16] P. García-Sánchez, A. Tonda, A. García , G. Squillero, and J. J. Guervós, “Automated Playtesting in Collectible Card Games using Evolutionary Algorithms: A Case Study in Hearthstone,” Knowledge Based Systems, pp. 133-146, 2018.
[17] Identifying Deck Archetypes, (https://tempostorm.com/articles/identifying-deck-archetypes), 2016.
[18] A. Stiegler, C. Messerschmidt, J. Maucher, and K. Dahal, “Hearthstone Deck-Construction with a Utility System,” in Software, Knowledge, Information Management & Applications (SKIMA), 2016 10th International Conference on. IEEE, pp. 21–28, 2016.
[19] S. J. Bjørke, and K. A. Fludal, “Deckbuilding in Magic: The Gathering using a Genetic Algorithm,” Master’s thesis, NTNU, 2017.
[20] LoCM GitHub https://github.com/acatai/Strategy-Card-Game-AI-Competition
[21] LoCM COG 2020參賽選手操作說明https://github.com/acatai/Strategy-Card-Game-AI-Competition/blob/master/docs/COG20/COG2020-slides.pdf