無界：一個生成式無限遊戲，模擬角色生活。

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

我們介紹了生成式無限遊戲的概念，這是一種視頻遊戲，通過使用生成模型超越了傳統有限、硬編碼系統的界限。受到詹姆斯·P·卡爾斯(James P. Carse)對有限和無限遊戲的區分的啟發，我們利用生成式人工智慧的最新進展來創建《無界》：一款完全封裝在生成模型中的角色生活模擬遊戲。具體來說，《無界》從沙盒生活模擬中汲取靈感，讓您可以通過餵食、與之互動和引導您的虛擬角色在虛擬世界中進行互動 - 這些互動機制由一個大型語言模型(LLM)生成，其中一些可能是新興的。為了開發《無界》，我們提出了在LLM和視覺生成領域的技術創新。具體來說，我們提出：(1)一個專門的、精煉的大型語言模型(LLM)，動態生成遊戲機制、敘事和角色互動，並且是實時的；(2)一個新的動態區域圖像提示適配器(IP-Adapter)用於視覺模型，確保在多個環境中對角色進行一致而靈活的視覺生成。我們通過定性和定量分析來評估我們的系統，顯示與傳統相關方法相比，在角色生活模擬、用戶指導、敘事連貫性以及角色和環境的視覺一致性方面都取得了顯著的改進。

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.