无边界：一个生成式无限游戏，模拟角色生活。

Unbounded: A Generative Infinite Game of Character Life Simulation

October 24, 2024

作者: Jialu Li, Yuanzhen Li, Neal Wadhwa, Yael Pritch, David E. Jacobs, Michael Rubinstein, Mohit Bansal, Nataniel Ruiz

cs.AI

摘要

我们引入了生成式无限游戏的概念，这是一种视频游戏，通过使用生成模型超越了传统有限、硬编码系统的界限。受詹姆斯·P·卡斯对有限和无限游戏的区分启发，我们利用生成式人工智能的最新进展创造了《无边》：一款完全封装在生成模型中的角色生活模拟游戏。具体而言，《无边》汲取了沙盒生活模拟的灵感，允许您通过LLM生成的开放式机制与您的自主虚拟角色在虚拟世界中互动，包括喂养、玩耍和引导，其中一些机制可能是新兴的。为了开发《无边》，我们在LLM和视觉生成领域提出了技术创新。具体而言，我们提出：（1）一种专门的、精炼的大型语言模型（LLM），动态生成游戏机制、叙事和角色互动，并且（2）一种新的动态区域图像提示适配器（IP-Adapter）用于视觉模型，确保在多个环境中对角色进行一致而灵活的视觉生成。我们通过定性和定量分析评估了我们的系统，展示了与传统相关方法相比，在角色生活模拟、用户指导、叙事连贯性以及角色和环境的视觉一致性方面的显著改进。

English

We introduce the concept of a generative infinite game, a video game that transcends the traditional boundaries of finite, hard-coded systems by using generative models. Inspired by James P. Carse's distinction between finite and infinite games, we leverage recent advances in generative AI to create Unbounded: a game of character life simulation that is fully encapsulated in generative models. Specifically, Unbounded draws inspiration from sandbox life simulations and allows you to interact with your autonomous virtual character in a virtual world by feeding, playing with and guiding it - with open-ended mechanics generated by an LLM, some of which can be emergent. In order to develop Unbounded, we propose technical innovations in both the LLM and visual generation domains. Specifically, we present: (1) a specialized, distilled large language model (LLM) that dynamically generates game mechanics, narratives, and character interactions in real-time, and (2) a new dynamic regional image prompt Adapter (IP-Adapter) for vision models that ensures consistent yet flexible visual generation of a character across multiple environments. We evaluate our system through both qualitative and quantitative analysis, showing significant improvements in character life simulation, user instruction following, narrative coherence, and visual consistency for both characters and the environments compared to traditional related approaches.