Unbounded: A Generative Infinite Game of Character Life Simulation
Jialu Li, Yuanzhen Li, Neal Wadhwa, Yael Pritch, David E. Jacobs,, Michael Rubinstein, Mohit Bansal, Nataniel Ruiz
TL;DR
Unbounded is a novel generative infinite game that uses advanced AI models to create a dynamic, open-ended virtual world with autonomous characters, enabling unprecedented interactive and emergent gameplay experiences.
Contribution
The paper introduces a new concept of a generative infinite game and develops innovative AI models, including a specialized LLM and a visual prompt adapter, to enable open-ended character life simulation.
Findings
Significant improvements in narrative coherence and visual consistency.
Enhanced user instruction following and character autonomy.
Demonstrated open-ended, emergent gameplay capabilities.
Abstract
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…
Peer Reviews
Decision·ICLR 2025 Poster
The main strengths of the paper are (1) the originality of entirely basing a virtual pet game on LLMs, (2) the significance of the two primary technical contributions to figure coherent image generation and real time LLM application uses, and (3) the quality of the image portion of the evaluation/experiments. The paper is also overall well-written, especially in terms of the technical aspects. These primarily justify the positive aspects of my above scores.
The paper has two major weaknesses in its present draft, the way it positions itself in terms of prior work and the evaluation. ### Prior Work The authors do not appear to have engaged with the field of technical games research at all. This is a shame, as their game can be understood as an AI-based game [1] or specifically a NN game [2]. More broadly, the authors' work in terms of generation would fit into the Procedural Content Generation paradigm [3]. There is a 3+ decades long history of w
This is an ambitious piece of work, tackling difficult technical issues in balancing generation and interaction, as well as various training and fine-tuning protocols. It appears to have innovated on a number of aspects, for instance the dynamic mask to balance character and environment generation. It gives some interesting, detailed, insights such as those of Figure 4. The improvement over IP-Adapter thus appears more than incremental. Another strong points is the Small LLM distillation framewo
From a fundamental perspective, there is a lack of awareness of some game design issues. The introduction is relatively naïve considering how these issues are addressed in game/play theory (Caillois, Huizinga). With the fine line between simulation and entertainment, and notwithstanding the reference to The Sims and Tamagotchi, contemporary audiences tend to have gameplay expectations that can only be met with sustained and meaningful (in the narrative sense) interactions. This feeds into the ov
Videos
Taxonomy
TopicsArtificial Intelligence in Games
Methods[[Refund`Get®]]How do I get American Airlines to respond? · Adapter