КФУ. Карточка публикации. Real-Time Generative Simulation of a Game Environment

КАЗАНСКИЙ
ФЕДЕРАЛЬНЫЙ УНИВЕРСИТЕТ

RUS

- EN
- 中文
- ES

REAL-TIME GENERATIVE SIMULATION OF A GAME ENVIRONMENT

Форма представления

Статьи в зарубежных журналах и сборниках

Год публикации

2025

Язык

английский

Авторы, сотрудники КФУ

Большаков Эдуард Сергеевич, автор

Кугуракова Влада Владимировна, автор

Библиографическое описание на языке оригинала

Bolshakov ES, Kugurakova VV, Real-Time Generative Simulation of a Game Environment//AUTOMATIC DOCUMENTATION AND MATHEMATICAL LINGUISTICS. - 2025. - Vol.59, Is.SUPPL2. - P.S75-S85.

Аннотация

Abstract—This paper explores the potential of generative neural network simulations, focusing on the application of reinforcement learning methods and neural world models for creating interactive worlds. Key achievements in agent training using reinforcement learning are discussed. Special attention is given to neural world models, as well as generative models such as Oasis, DIAMOND, Genie, and GameNGen, which employ diffusion networks to generate realistic and interactive game worlds. The opportunities and limitations of generative simulation models are examined, including issues that are related to error accumulation and memory constraints and their impact on the quality of generation. The conclusion presents suggestions for future research directions.

Ключевые слова

video games, game environment, generative simulation, reinforcement learning, generative neural networks, gameplay simulation, world models

Название журнала

AUTOMATIC DOCUMENTATION AND MATHEMATICAL LINGUISTICS

URL

https://link.springer.com/article/10.3103/S0005105525700700

Пожалуйста, используйте этот идентификатор, чтобы цитировать или ссылаться на эту карточку

https://repository.kpfu.ru/?p_id=321045

Полная запись метаданных

Поле DC	Значение	Язык
dc.contributor.author	Большаков Эдуард Сергеевич	ru_RU
dc.contributor.author	Кугуракова Влада Владимировна	ru_RU
dc.date.accessioned	2025-01-01T00:00:00Z	ru_RU
dc.date.available	2025-01-01T00:00:00Z	ru_RU
dc.date.issued	2025	ru_RU
dc.identifier.citation	Bolshakov ES, Kugurakova VV, Real-Time Generative Simulation of a Game Environment//AUTOMATIC DOCUMENTATION AND MATHEMATICAL LINGUISTICS. - 2025. - Vol.59, Is.SUPPL2. - P.S75-S85.	ru_RU
dc.identifier.uri	https://repository.kpfu.ru/?p_id=321045	ru_RU
dc.description.abstract	AUTOMATIC DOCUMENTATION AND MATHEMATICAL LINGUISTICS	ru_RU
dc.description.abstract	Abstract—This paper explores the potential of generative neural network simulations, focusing on the application of reinforcement learning methods and neural world models for creating interactive worlds. Key achievements in agent training using reinforcement learning are discussed. Special attention is given to neural world models, as well as generative models such as Oasis, DIAMOND, Genie, and GameNGen, which employ diffusion networks to generate realistic and interactive game worlds. The opportunities and limitations of generative simulation models are examined, including issues that are related to error accumulation and memory constraints and their impact on the quality of generation. The conclusion presents suggestions for future research directions.	ru_RU
dc.language.iso	ru	ru_RU
dc.subject	video games	ru_RU
dc.subject	game environment	ru_RU
dc.subject	generative simulation	ru_RU
dc.subject	reinforcement learning	ru_RU
dc.subject	generative neural networks	ru_RU
dc.subject	gameplay simulation	ru_RU
dc.subject	world models	ru_RU
dc.title	Real-Time Generative Simulation of a Game Environment	ru_RU
dc.type	Статьи в зарубежных журналах и сборниках	ru_RU