Collectible Card Games Research Articles

CreativeStone: A Creativity Booster for Hearthstone Card Decks

Digital Collectible Card Games (DCCG) rely on human expertise to create competitive card decks. The most effective decks are shared and become popular among players through online communities. Players then keep enhancing those decks by replacing cards and testing those new deck variations in online arenas. This fine-tuning process is time-consuming and most of the time leads to small improvements in the players win rate. This paper presents CreativeStone, a creativity booster for Hearthstone card decks. Our creativity-guided approach uses a genetic algorithm and the Regent-Dependent Creativity (RDC) metric to identify the core cards of an existing deck, and then improves it towards a more valuable and novel deck by adding cards that are synergic to the core cards, but also different from the ones in the original deck. Our experimental results show that CreativeStone can boost even legendary decks, outperforming handcrafted ones by 21% in win rate.

Player Identification and Next-Move Prediction for Collectible Card Games with Imperfect Information

Effectively identifying an individual and predicting their future actions is a material aspect of player analytics, with applications for player engagement and game security. Collectible card games are a fruitful test space for studying player identification, given that their large action spaces allow for flexibility in play styles, thereby facilitating behavioral analysis at the individual, rather than the aggregate, level. Further, once players are identified, modeling the differences between individuals may allow us to preemptively detect patterns that foretell future actions. As such, we use the virtual collectible card game "Legends of Code and Magic" to research both of these topics. Our main contributions to the task are the creation of a comprehensive dataset of Legends of Code and Magic game states and actions, extensive testing of the minimum information and computational methods necessary to identify an individual from their actions, and examination of the transferability of knowledge collected from a group to unknown individuals.

A Ruse by Any Other Name: Comparing Loot Boxes and Collectible Card Games Using Magic Arena

The convergence of gaming and gambling, known as "gamblification", has been a topic of increasing interest in recent years. Loot boxes, i.e., rewards offering randomized content in exchange for money or time, have been a particular focal point. Research has shown links between excessive loot box consumption and problematic consumption behaviors, leading to several attempts to regulate loot boxes. Arguments against regulation have been that loot boxes are conceptually and structurally akin to other unregulated game formats, such as collectible card games. However, this discourse is often without deeper analysis of the mechanics of different products at the center of convergence. Therefore, to add to this knowledge, this article examines the similarities and differences between booster packs in Magic Arena, their physical counterparts in Magic: The Gathering, and loot boxes included in digital games. Particular attention is paid to the ways in which these booster packs compare to loot boxes in terms of consumption patterns, visual appearance, contextual factors, and regulation. Analysis reveals that digital booster packs in Magic Arena differ from both loot boxes and physical card packs, both due to their direct impact on gameplay, and their unique features afforded by the digital environment in which they exist.

Towards sample efficient deep reinforcement learning in collectible card games

Collectible card games (CCGs) are widely-played games in which players build a deck from a set of custom cards and use it to battle each other. They are notoriously more challenging than games such as Go and Texas Hold’em Poker, the protagonists of recent breakthroughs in game-playing AI. Deep reinforcement learning approaches have recently become state-of-the-art in CCGs, although requiring huge amounts of computational power to train. In this paper, we propose a collection of deep reinforcement learning approaches to battling in CCGs that are trainable on a single desktop computer. Each approach tries different mechanisms to increase sample efficiency. We use Legends of Code and Magic, a CCG designed for AI research, as a testbed and compare our approaches to each other, considering their win rate and other metrics. Then, we discuss the position of our approaches regarding the current literature, their limitations, directions of improvement, and extension to commercial CCGs.

Player Identification for Collectible Card Games with Dynamic Game States

Collectible card games are a fruitful test space for studying resource allocation and battle strategy, given that their structures promote reactionary combat styles and allow players to obtain variable amounts of combat power by expending fixed resources. However, their large action spaces also allow for flexibility in play styles, thus facilitating behavioral analysis at the individual level rather than the aggregate level. When presented with the same options and the same amount of resources, a player's selection of cards and their choice of moves gives insight into their unique play style and decision-making tendencies. As such, we use the virtual collectible card game Legends of Code and Magic to determine whether we can identify a player from their actions and, conversely, predict the future actions of a known player. Our main contributions to this task are the creation of a comprehensive dataset of Legends of Code and Magic game states and actions, as well as the first use of large transformer-based language models to address this problem.

Conceptual metaphor in trading card games

Abstract The current study aims to demonstrate that trading card games (TCGs), also called collectible card games (CCGs), represent a potentially fruitful area of research in metaphor studies. A popular trading card game called Yu-Gi-Oh! is examined, and the argument is made that players utilize the cognitive mechanisms of conceptual metaphor to conceptualize its core game mechanics. Based on the results of a survey (n = 186) it was concluded that players conceptualize such game mechanics in line with the logics inherent in the Location Event Structure Metaphor, in conjunction with the metaphors birth is arrival, life is being present here, and death is departure. This implies that it is precisely the embodied cognitive mechanisms of conceptual metaphor which allow for a shared, intersubjective understanding between players to exist regarding the meanings of various gameplay scenarios in Yu-Gi-Oh!, and possibly in many other trading card games as well.

Learning multimodal entity representations and their ensembles, with applications in a data-driven advisory framework for video game players

We investigate the impact of combining multiple representations derived from heterogeneous data sources on the performance of machine learning (ML) models. In particular, we experimentally compare the approach in which independent models are trained on data representations from different sources with the one in which a single model is trained on joined data representations. As a case study, we discuss various entity representation learning methods and their applications in our data-driven advisory framework for video game players, called SENSEI. We show how to use the discussed methods to learn representations of cards and decks for two popular collectible card games (CCGs), namely Clash Royale (CR) and Hearthstone: Heroes of Warcraft (HS). Then, we follow our approach to create ML models which constitute the back-end for several out of SENSEI’s end-user functionalities. When learning representations, we consider techniques inspired by the NLP domain, as they allow us to create embeddings which capture various aspects of similarity between entities. We put them together with representations composed of manually engineered features and standard bags-of-cards. On top of that, we propose a new end2end deep learning architecture with an attention mechanism aimed at reflecting meaningful inter-entity interactions.

Exploring reinforcement learning approaches for drafting in collectible card games

Collectible card games (CCGs), such as Magic: the Gathering and Hearthstone, are played by tens of millions worldwide and are known for their usually large and intricate rules. From an artificial intelligence (AI) standpoint, playing CCGs consists of two interdependent tasks: deck-building and battling. This paper presents three deep reinforcement learning approaches for deck-building in the arena mode of CCGs. Our approaches are trained in self-play and differ in the handling of past information when drafting new cards for a deck. We formulate the problem in a game-agnostic manner and perform experiments on Legends of Code and Magic, a CCG designed for AI research. Considering the win rate of the decks when used by fixed battling agents, the results show that our trained drafting agents outperform the best ones available for the game and do so by building very different decks. We also reenact the Strategy Card Game AI competition and show that our best drafting strategy improves the win rate of a baseline competitor by 14.9 and 12.7 percentage points in the 2019 and 2020 editions.

Foreign Yet Familiar: J. L. Borges’ Book of Imaginary Beings and Other Cultural Ferrymen in Japanese Fantasy Games

This paper considers J. L. Borges’ Book of Imaginary Beings as a vector for the cultural transfer of folkloric, mythological, religious, and literary motifs from foreign cultures to Japanese video games and collectible card games. My analysis relies upon Michel Espagne’s cultural transfer theories and discusses not only the Book of Imaginary Beings but also other vectors of transfer, such as the roleplaying game Dungeons & Dragons. I focus on four specific motifs from different cultural spheres, whose introduction to Japanese video games can be retraced to Borges’ bestiary: The carbuncle, the catoblepas, the peryton, and Kujata. Thus, this paper presents a case study of the cross-cultural influence of literary works on games. Furthermore, it underscores the need for a deeper consideration of the cultural influences found in games and of games as agents of cultural transfers.

Deep Learning Techniques for Explainable Resource Scales in Collectible Card Games

In collectible card games, developers face the challenge of creating new, and interesting cards that are not too strong or game-breaking, retaining the game’s overall balance. Over time, this becomes challenging due to the sheer volume of the published content. In this article, we propose a framework for generating models capable of recommending resource scales, a pivotal point in balancing. We evaluate the usage of several state-of-the-art neural architectures to learn representations for text followed by gradient boosting decision trees to incorporate remaining features. Throughout our analysis, we present various explanation tools that should empower game developers, and aid them with new insights. In particular, we present the sets of words that drive the model in diverse situations, such as when it was inaccurate by a small margin. We also exhibit instances where textual features cannot give an accurate prediction, requiring additional information. Our method achieves a mean reciprocal rank of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$+0.8$</tex-math></inline-formula> when evaluated on popular card games, even though superficially identical cards might have distinct costs.

A Conservative Metric of Power Creep

Collectible card games are taking up more space in popular culture with traditional paper card games even embracing e-sports. However, longevity in such games is not as common, with some suspecting power creep as a culprit behind why some of these games fail. Yet, Magic: the Gathering has not just survived but thrived for over 25 years with the game’s designers publicly stating their aim to keep curbing power creep. Therefore, it is of interest to determine the rate of power creep in the game. Herein, we formally define a conservative metric power creep and calculate its occurrence in the game of Magic: the Gathering. Although having an increasing rate, power creep appears low with an average of 1.56 strictly better card faces released per year.

Modular Computational Critics for Games

Formal game modeling tools could support the automated analysis of game rules and rapid automated play-testing, but are not widely used. Furthermore, existing game design support tools are often limited to very specific classes of game, require significant programming expertise to use or customize, or are fully-automatic tools with limited affordances for human designers. We therefore propose a framework for authoring computational game design critics and a new game definition language (Gamelan) grounded in the conventions of board game rules. We show how a set of these critics could have detected specific, attested design problems in the development of Donald X. Vaccarino's influential card game Dominion. We also illustrate an extension of this approach to other collectible card games, turn-taking games, and games in general.

Mystical Tutor: A Magic: The Gathering Design Assistant via Denoising Sequence-to-Sequence Learning

Procedural Content Generation (PCG) has seen heavy focus on the generation of levels for video games, aesthetic content, and on rule creation, but has seen little use in other domains. Recently, the ready availability of Long Short Term Memory Recurrent Neural Networks (LSTM RNNs) has seen a rise in text based procedural generation, including card designs for Collectible Card Games (CCGs) like Hearthstone or Magic: The Gathering. In this work we present a mixed-initiative design tool, Mystical Tutor, that allows a user to type in a partial specification for a card and receive a full card design. This is achieved by using sequence-to-sequence learning as a denoising sequence autoencoder, allowing Mystical Tutor to learn how to translate from partial specifications to full.

Links between problem gambling and spending on booster packs in collectible card games: A conceptual replication of research on loot boxes.

Loot boxes are digital containers of randomised rewards present in some video games which are often purchasable for real world money. Recently, concerns have been raised that loot boxes might approximate traditional gambling activities, and that people with gambling problems have been shown to spend more on loot boxes than peers without gambling problems. Some argue that the regulation of loot boxes as gambling-like mechanics is inappropriate because similar activities which also bear striking similarities to traditional forms of gambling, such as collectable card games, are not subject to such regulations. Players of collectible card games often buy sealed physical packs of cards, and these 'booster packs' share many formal similarities with loot boxes. However, not everything which appears similar to gambling requires regulation. Here, in a large sample of collectible card game players (n = 726), we show no statistically significant link between in real-world store spending on physical booster and problem gambling (p = 0.110, η2 = 0.004), and a trivial in magnitude relationship between spending on booster packs in online stores and problem gambling (p = 0.035, η2 = 0.008). Follow-up equivalence tests using the TOST procedure rejected the hypothesis that either of these effects was of practical importance (η2 > 0.04). Thus, although collectable card game booster packs, like loot boxes, share structural similarities with gambling, it appears that they may not be linked to problem gambling in the same way as loot boxes. We discuss potential reasons for these differences. Decisions regarding regulation of activities which share structural features with traditional forms of gambling should be made on the basis of definitional criteria as well as whether people with gambling problems purchase such items at a higher rate than peers with no gambling problems. Our research suggests that there is currently little evidence to support the regulation of collectable card games.

Optimizing Hearthstone agents using an evolutionary algorithm

Digital collectible card games are not only a growing part of the video game industry, but also an interesting research area for the field of computational intelligence. This game genre allows researchers to deal with hidden information, uncertainty and planning, among other aspects. This paper proposes the use of evolutionary algorithms (EAs) to develop agents who play a card game, Hearthstone, by optimizing a data-driven decision-making mechanism that takes into account all the elements currently in play. Agents feature self-learning by means of a competitive coevolutionary training approach, whereby no external sparring element defined by the user is required for the optimization process. One of the agents developed through the proposed approach was runner-up (best 6%) in an international Hearthstone Artificial Intelligence (AI) competition. Our proposal performed remarkably well, even when it faced state-of-the-art techniques that attempted to take into account future game states, such as Monte-Carlo Tree search. This outcome shows how evolutionary computation could represent a considerable advantage in developing AIs for collectible card games such as Hearthstone.

The Many AI Challenges of Hearthstone

Since the inception of artificial intelligence, games have benchmarked algorithmic advances. Recent success in classic board games such as Chess and Go have left space for video games that pose related yet different sets of challenges. With this shifted focus, the set of AI problems associated with video games has expanded from simply playing these games to win, to include playing games in particular styles, generating game content, modeling players, etc. Different games pose different challenges for AI systems, and several such AI challenges can typically be addressed in the same game. In this article we analyze the popular collectible card game Hearthstone published by Blizzard in 2014, and describe a varied set of interesting AI challenges it poses. Despite their popularity and associated interesting challenges, collectible card games are relatively understudied in the AI community. By analyzing a single game in-depth, we get a glimpse of the entire field of AI and games through the lens of a single game, discovering a few new variations on existing research topics.

May the passion be with you: The addictive potential of collectible card games, miniatures, and dice of the Star Wars universe.

Background and aimsIn recent years, we have witnessed a growing research interest in behavioral addictions and in pleasurable behaviors that generate a certain discomfort in the people who engage in them. The objective of this study was to assess if users of collectible card games, miniatures, and dice from the Star Wars Universe Games (SWUG) may also present criteria of addiction and if the presence of these criteria is related to demographic variables, game-playing habits, and other variables.MethodsSWUG players were contacted through specialized gaming chats, and 218 of them completed the Internet Gaming Disorder Scale – Short Form (IGDS-SF9), a scale that assesses motivation to engage in the game (Massively Multiplayer Online Motivations Scale), the Rosenberg Self-Esteem Questionnaire, the Diener Satisfaction with Life Scale, and a question for the self-assessment of addiction.ResultsSignificant predictors of addictive symptoms were the motivation to seek dissociation and (negatively) self-esteem. Users more significantly dedicate indirect hours to the game (thinking about the game, preparing material, etc.) than to actually playing. No participant could be considered pathologically addicted, as no one scored above the tentative cut-off point of the IGDS-SF9.Discussion and conclusionsDespite the fact that many players considered themselves “addicted” and some presented various economic and family problems related to their activity, it was found that playing these games could not be equated to true addictive behavior, since no player had scores above the cut-off point. This finding contributes to current discussions about the tendency to overestimate excessive pleasurable behaviors.

Procedural Content Generation via Machine Learning (PCGML)

This survey explores procedural content generation via machine learning (PCGML), defined as the generation of game content using machine learning models trained on existing content. As the importance of PCG for game development increases, researchers explore new avenues for generating high-quality content with or without human involvement; this paper addresses the relatively new paradigm of using machine learning (in contrast with search-based, solver-based, and constructive methods). We focus on what is most often considered functional game content, such as platformer levels, game maps, interactive fiction stories, and cards in collectible card games, as opposed to cosmetic content, such as sprites and sound effects. In addition to using PCG for autonomous generation, cocreativity, mixed-initiative design, and compression, PCGML is suited for repair, critique, and content analysis because of its focus on modeling existing content. We discuss various data sources and representations that affect the generated content. Multiple PCGML methods are covered, including neural networks: long short-term memory networks, autoencoders, and deep convolutional networks; Markov models: $n$-grams and multi-dimensional Markov chains; clustering; and matrix factorization. Finally, we discuss open problems in PCGML, including learning from small data sets, lack of training data, multilayered learning, style-transfer, parameter tuning, and PCG as a game mechanic.

HearthBot: An Autonomous Agent Based on Fuzzy ART Adaptive Neural Networks for the Digital Collectible Card Game HearthStone

Digital collectible card games, as partially observable games based on alternating turns, such as HearthStone, have been the most played card games in recent years, where the main challenge is the creation of strategies capable of subdue the enemy's moves. From the artificial intelligence perspective, the space of possible strategies is large and dynamic due to the number of cards and actions combinations and also to randomness, which makes the design of efficient autonomous agents a hard problem. This paper presents HearthBot, an autonomous agent that plays HearthStone through an adaptive neural network inspired in the fuzzy adaptive resonance associative map and adaptive resonance theory map. This paper also proposes a new mechanism to categorize and predict information to overcome the overgeneralization problem from those networks. Furthermore, the proposed solution was implemented as a parallel adaptive neural network for a graphics processing unit that achieves a performance compatible with the ones obtained for deep learning methods. HearthBot win rate was evaluated in two experiments playing against a Monte Carlo tree search heuristic with competitive decks on a HearthStone simulator called Metastone. Results show that the proposed solution allows HearthBot to obtain an average win rate performance of 80% against known decks and 70% against unknown decks.

Automated playtesting in collectible card games using evolutionary algorithms: A case study in hearthstone

Collectible card games have been among the most popular and profitable products of the entertainment industry since the early days of Magic: The GatheringTM in the nineties. Digital versions have also appeared, with HearthStone: Heroes of WarCraftTM being one of the most popular. In Hearthstone, every player can play as a hero, from a set of nine, and build his/her deck before the game from a big pool of available cards, including both neutral and hero-specific cards. This kind of games offers several challenges for researchers in artificial intelligence since they involve hidden information, unpredictable behaviour, and a large and rugged search space. Besides, an important part of player engagement in such games is a periodical input of new cards in the system, which mainly opens the door to new strategies for the players. Playtesting is the method used to check the new card sets for possible design flaws, and it is usually performed manually or via exhaustive search; in the case of Hearthstone, such test plays must take into account the chosen hero, with its specific kind of cards. In this paper, we present a novel idea to improve and accelerate the playtesting process, systematically exploring the space of possible decks using an Evolutionary Algorithm (EA). This EA creates HearthStone decks which are then played by an AI versus established human-designed decks. Since the space of possible combinations that are play-tested is huge, search through the space of possible decks has been shortened via a new heuristic mutation operator, which is based on the behaviour of human players modifying their decks. Results show the viability of our method for exploring the space of possible decks and automating the play-testing phase of game design. The resulting decks, that have been examined for balancedness by an expert player, outperform human-made ones when played by the AI; the introduction of the new heuristic operator helps to improve the obtained solutions, and basing the study on the whole set of heroes shows its validity through the whole range of decks.