Scholarlink

Abstract <p>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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Real-Time Generative Simulation of a Game Environment

  • 期刊论文

  • 发表日期：

    2025年10月1日

查看全文
  • E. S. Bolshakov,
  • V. V. Kugurakova

摘要

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.