Abstract
While Poker, as a family of games, has been studied extensively in the last decades, collectible card games have seen relatively little attention. Only recently have we seen an agent that can compete with professional human players in Hearthstone, one of the most popular collectible card games. Although artificial agents must be able to work with imperfect information in both of these genres, collectible card games pose another set of distinct challenges. Unlike in many poker variants, agents must deal with state space so vast that even enumerating all states consistent with the agent's beliefs is intractable, rendering the current search methods unusable and requiring the agents to opt for other techniques. In this paper, we investigate the strength of such techniques for this class of games. Namely, we present preliminary analysis results of ByteRL, the state-of-the-art agent in Legends of Code and Magic and Hearthstone. Although ByteRL beat a top-10 Hearthstone player from China, we show that its play in Legends of Code and Magic is highly exploitable.
Abstract (translated)
尽管扑克作为一家人口游戏已经深入研究了几十年，收藏卡牌游戏却受到了相对较少的关注。直到最近，我们才看到了一个可以与职业人类玩家在《英雄联盟：魔兽世界》等最受欢迎的收藏卡牌游戏中竞技的代理。尽管人工智能代理必须能够处理这两类游戏中不完美的信息，但收藏卡牌游戏又提出了另一组独特的挑战。与许多扑克变体不同，代理必须处理状态空间如此之广，以至于连列出所有与代理信念一致的状态都是不可行的，使得当前的搜索方法无法使用，并要求代理选择其他技术。在本文中，我们研究了这类游戏中所使用的这些技术的强度。具体来说，我们介绍了《英雄联盟：魔兽世界》和《英雄联盟：激战峡谷》中代表最先进水平的代理ByteRL的初步分析结果。尽管ByteRL在击败中国排名前十的《英雄联盟：魔兽世界》玩家方面表现出色，但我们表明，它在《英雄联盟：激战峡谷》中的表现具有高度的被 exploitation 性。
URL
https://arxiv.org/abs/2404.16689
