Evolving Evaluation Functions for Collectible Card Game AI

Miernik, Radoslaw; Kowalski, Jakub

doi:10.5220/0010806900003116

Cited by 4 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…: choosing a play style, identifying patterns in the opponent's actions, and scaling based on difficulty (Hoover et al 2020). Furthermore, current best-known methods of approaching these challenges vary widely based on the game; simple tree searches have shown large improvements in AI performance on LoCM (Klasiński, Meller, and Witkowski 2020;Miernik and Kowalski 2022), but more complex games like Hearthstone require neural networks (Grad 2017) to assist player performance. Some CCGs, such as Hearthstone and Legends of Code and Magic (LoCM) (Kowalski and Miernik 2018), have been designed to play in an entirely digital form (thus reducing some of the logistics required to develop an AI), but these have significantly smaller spaces of card effects when compared to older physical card games such as MtG and Yu-Gi-Oh!.…”

Section: Procedurementioning

confidence: 99%

Code Generation for Collectible Card Games with Complex APIs

Licato

Fields

Hollis

2023

FLAIRS

View full text Add to dashboard Cite

Large pre-trained language models (LMs) such as GPT-3 Codex are able to generate code remarkably well given prompts of natural language text. But if we want to use such LMs to generate code compatible with a specific API or library (e.g., an API which provides the environments in which certain rules, laws, or orders are to be carried out), the amount of computational and data resources required to fine-tune such models can be cost prohibitive to most organizations. Given these practical limitations, is it possible to utilize these massive code-generation LMs to write code compatible with a given API? We develop an algorithm that selects code examples using a smaller LM trained to predict which features of an API are likely to be used in the resulting code, which is a simpler problem than actually generating the code. The selected examples are then used to build a prompt for the larger LM, which in turn generates the final code. We demonstrate our results on a benchmark dataset derived from the collectible card game "Magic: the Gathering," and obtain state-of-the-art results.

show abstract

Section: Procedurementioning

confidence: 99%

Code Generation for Collectible Card Games with Complex APIs

Licato

Fields

Hollis

2023

FLAIRS

View full text Add to dashboard Cite

show abstract

“…An approach tailored to the arena game mode in LOCM, extending EA with active genes to improve learning efficiency, was described in [26]. Another study analyzes the influence of representation and the choice of opponent used to test the model on the quality of learned heuristics [27].…”

Section: Ccg Deckbuilding and Game Balancingmentioning

confidence: 99%

Evolutionary Approach to Collectible Arena Deckbuilding using Active Card Game Genes

Kowalski

Miernik

2020

2020 IEEE Congress on Evolutionary Computation (CEC)

View full text Add to dashboard Cite

This paper concludes five years of AI competitions based on Legends of Code and Magic (LOCM), a small Collectible Card Game (CCG), designed with the goal of supporting research and algorithm development. The game was used in a number of events, including Community Contests on the CodinGame platform, and Strategy Card Game AI Competition at the IEEE Congress on Evolutionary Computation and IEEE Conference on Games. LOCM has been used in a number of publications related to areas such as game tree search algorithms, neural networks, evaluation functions, and CCG deckbuilding.We present the rules of the game, the history of organized competitions, and a listing of the participant and their approaches, as well as some general advice on organizing AI competitions for the research community. Although the COG 2022 edition was announced to be the last one, the game remains available and can be played using an online leaderboard arena.

show abstract

“…As such, CCGs are a useful platform for examining resource allocation and rapid strategy development under pressure (Adinolf and Turkay 2011). However, their broad action spaces, imperfect information, and far-reaching planning structures also allow almost infinitely many possible decks and innovative multi-turn sequences, enabling the representation of individualized cognitive distinctions rather than generalized assumptions derived from the collective performance of numerous players (Miernik and Kowalski 2022;Yao et al 2022). This makes CCGs an appropriate medium for researching the intersections between AI, gaming, and security.…”

Section: Introductionmentioning

confidence: 99%

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

Fields,

Licato

2023

AIIDE

View full text Add to dashboard Cite

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.

show abstract

Evolving Evaluation Functions for Collectible Card Game AI

Cited by 4 publications

References 27 publications

Code Generation for Collectible Card Games with Complex APIs

Code Generation for Collectible Card Games with Complex APIs

Evolutionary Approach to Collectible Arena Deckbuilding using Active Card Game Genes

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

Contact Info

Product

Resources

About