Ensemble Determinization in Monte Carlo Tree Search for the Imperfect Information Card Game Magic: The Gathering

Cowling, Peter I.; Ward, C. D.; Powley, Edward J.

doi:10.1109/tciaig.2012.2204883

Cited by 66 publications

(42 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Knowledge about the hostile hand is usually inaccessible and thus there is a strong factor of uncertainty. With card pools of several hundreds or even thousands, this leads to a huge variety in the potential action space for the same game state, leading to an explosion in branching factors for TCGs, as Cowling et al [5] found. A common technique for MCTS approaches in situations with uncertainty is reducing the problem to a perfect information game through determinization.…”

Section: Monte Carlo Tree Searchmentioning

confidence: 99%

“…Due to these properties, TCGs are already used in academic work, such as using Monte Carlo Tree Search to cover uncertainty [5] or card selection [6]. Other work, such as HoningStone [7], focuses on the creative aspects of selecting card combos.…”

mentioning

confidence: 99%

“…Other work, such as HoningStone [7], focuses on the creative aspects of selecting card combos. Mahlmann et al [19] introduce the deck-building card game "Dominion" 5 as a testbed to construct interesting decks. Although RTS research saw a far greater variety of approaches deployed, we want to propose TCGs as a testbed for the higher-level planning problems, which are often hard to work on in RTS games, as they typically tie towards micromanagement, thus requiring a multi-agent approach to cover all the aspects of a full RTS: If the underlying micromanagement is not solved sufficiently well, higher-level planning will be limited, too.…”

mentioning

confidence: 99%

“…Other common metrics for player-level AI evaluation, such as runtime performance and controllability, are secondary. This 5 Rio Grande Games, 2008 (http://riograndegames.com/Game/278-Dominion) 6 Lunarch Studios (http://blog.prismata.net/2014/12/17/the-prismata-ai/)…”

mentioning

confidence: 99%

See 3 more Smart Citations

Symbolic Reasoning for <italic>Hearthstone</italic>

et al. 2018

View full text Add to dashboard Cite

Abstract-Trading-Card-Games are an interesting problem domain for Game AI, as they feature some challenges, such as highly variable game mechanics, that are not encountered in this intensity in many other genres. We present an expert system forming a player-level AI for the digital Trading-Card-Game Hearthstone. The bot uses a symbolic approach with a semantic structure, acting as an ontology, to represent both static descriptions of the game mechanics and dynamic game-state memories. Methods are introduced to reduce the amount of expert knowledge, such as popular moves or strategies, represented in the ontology, as the bot should derive such decisions in a symbolic way from its knowledge base. We narrow down the problem domain, selecting the relevant aspects for a play-to-win bot approach and comparing an ontology-driven approach to other approaches such as machine learning and case-based reasoning. Upon this basis, we describe how the semantic structure is linked with the game-state and how different aspects, such as memories, are encoded. An example will illustrate how the bot, at runtime, uses rules and queries on the semantic structure combined with a simple utility system to do reasoning and strategic planning. Finally, an evaluation is presented that was conducted by fielding the bot against the stock "Expert" AI that Hearthstone is shipped with, as well as Human opponents of various skill levels in order to assess how well the bot plays. Evaluating how believable the bot reasons is assessed through a Pseudo-Turing test.

show abstract

Section: Monte Carlo Tree Searchmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Symbolic Reasoning for <italic>Hearthstone</italic>

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The Gathering (Ward and Cowling, 2009;Cowling et al, 2012), a card game similar to Hearthstone. These approaches however usually solve subproblems of the game they are applied to, and not the game itself, through the abstraction of many variables.…”

Section: Machine Learning and Video Gamesmentioning

confidence: 99%

Decision Making from Confidence Measurement on the Reward Growth using Supervised Learning - A Study Intended for Large-scale Video Games

Taralla

Qiu

Sutera

et al. 2016

Proceedings of the 8th International Conference on Agents and Artificial Intelligence

View full text Add to dashboard Cite

Abstract:Video games have become more and more complex over the past decades. Today, players wander in visuallyand option-rich environments, and each choice they make, at any given time, can have a combinatorial number of consequences. However, modern artificial intelligence is still usually hard-coded, and as the game environments become increasingly complex, this hard-coding becomes exponentially difficult. Recent research works started to let video game autonomous agents learn instead of being taught, which makes them more intelligent. This contribution falls under this very perspective, as it aims to develop a framework for the generic design of autonomous agents for large-scale video games. We consider a class of games for which expert knowledge is available to define a state quality function that gives how close an agent is from its objective. The decision making policy is based on a confidence measurement on the growth of the state quality function, computed by a supervised learning classification model. Additionally, no stratagems aiming to reduce the action space are used. As a proof of concept, we tested this simple approach on the collectible card game Hearthstone and obtained encouraging results.

show abstract

Neural Networks Models for Analyzing Magic: The Gathering Cards

Zilio

Prates

Lamb

2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Historically, games of all kinds have often been the subject of study in scientific works of Computer Science, including the field of machine learning. By using machine learning techniques and applying them to a game with defined rules or a structured dataset, it's possible to learn and improve on the already existing techniques and methods to tackle new challenges and solve problems that are out of the ordinary. The already existing work on card games tends to focus on gameplay and card mechanics. This work aims to apply neural networks models, including Convolutional Neural Networks and Recurrent Neural Networks, in order to analyze Magic: the Gathering cards, both in terms of card text and illustrations; the card images and texts are used to train the networks in order to be able to classify them into multiple categories. The ultimate goal was to develop a methodology that could generate card text matching it to an input image, which was attained by relating the prediction values of the images and generated text across the different categories.

show abstract

Ensemble Determinization in Monte Carlo Tree Search for the Imperfect Information Card Game Magic: The Gathering

Cited by 66 publications

References 32 publications

Symbolic Reasoning for <italic>Hearthstone</italic>

Symbolic Reasoning for <italic>Hearthstone</italic>

Decision Making from Confidence Measurement on the Reward Growth using Supervised Learning - A Study Intended for Large-scale Video Games

Neural Networks Models for Analyzing Magic: The Gathering Cards

Contact Info

Product

Resources

About