Symbolic Reasoning for Hearthstone
1 Symbolic Reasoning for Hearthstone Andreas Stiegler, Member, IEEE, Keshav Dahal, Senior Member, IEEE, Johannes Maucher, Member, IEEE, and Daniel Livingstone, Member, IEEE planning aspects and the reasoning systems required for it are Abstract—Trading-Card-Games are an interesting problem focus of our research. domain for Game AI, as they feature some challenges, such as A lot of reasoning and planning research is currently highly variable game mechanics, that are not encountered in this conducted for Real-Time-Strategy (RTS) games, such as intensity in many other genres. We present an expert system “StarCraft”4, as analyzed by Ontanón et al [1]. Reasoning and forming a player-level AI for the digital Trading-Card-Game Hearthstone. The bot uses a symbolic approach with a semantic planning in games, RTS games in particular, was promoted as structure, acting as an ontology, to represent both static an interesting research problem by Buro [2, 3] and by many descriptions of the game mechanics and dynamic game-state researchers since then [4]. In Hearthstone, as in RTS games, a memories. Methods are introduced to reduce the amount of lot of short and long term planning has to be done. RTS bots expert knowledge, such as popular moves or strategies, are typically split into micro- and macro-management, dealing represented in the ontology, as the bot should derive such with individual units or the large scale battle plan respectively. decisions in a symbolic way from its knowledge base. We narrow down the problem domain, selecting the relevant aspects for a The move selection in Hearthstone is arguably of similar play-to-win bot approach and comparing an ontology-driven complexity to typical planning tasks in RTS.
[Show full text]