The Many AI Challenges of Hearthstone

Abstract

Games have benchmarked AI methods since the inception of the field, with classic board games such as Chess and Go recently leaving room for video games with related yet different sets of challenges. The set of AI problems associated with video games has in recent decades expanded from simply playing games to win, to playing games in particular styles, generating game content, modeling players etc. Different games pose very different challenges for AI systems, and several different AI challenges can typically be posed by the same game. In this article we analyze the popular collectible card game Hearthstone (Blizzard 2014) and describe a varied set of interesting AI challenges posed by this game. Collectible card games are relatively understudied in the AI community, despite their popularity and the interesting challenges they pose. Analyzing a single game in-depth in the manner we do here allows us to see the entire field of AI and Games through the lens of a single game, discovering a few new variations on existing research topics.

Evolutionary Approach to Collectible Card Game Arena Deckbuilding using Active Genes

“…The problem of creating decks that will be effective for some given meta (usually understand as currently dominating set of opposing decks) is one of the key challenges for CCG domain [5]. In [12], the Hearthstone decks are evolved and tested for their strength via playing against a small number of predefined human-created decks.…”

“…The weight is put on particular game features that make designing successful AI players especially tricky, e.g., imperfect information, randomness, long term planning, and massive action space. One of the game genres containing all these game features is Collectible Card Games [5].…”

A Practical Solution to Handling Randomness and Imperfect Information in Monte Carlo Tree Search

“…We describe a relatively complete approach to using MCTS in a game with hidden information and random effects [19], [20]. However, the specific game we have chosen for this study is Hearthstone: Heroes of Warcraft, developed by Blizzard Entertainment [21]. Hearthstone is an immensely popular game having around 70 million active players.…”

Evolving Evaluation Functions for Collectible Card Game AI

“…One of the recently popular game-related AI testbeds are Collectible Card Games (e.g., Hearthstone [6], The Elder Scrolls: Legends [7]). Because they combine imperfect information, randomness, long-term planning, and massive action space, they impose many interesting challenges [8]. Also, the specific form of game state (combining global board features with features of individual cards) makes such games particularly suited for various forms of feature-based state evaluation utilizing human player knowledge.…”