用深度神经网络模拟可进化的智能体，探索人工生命中的开放式文化演化。
JaxLife: An Open-Ended Agentic Simulator
- 用可编程世界中的具身智能体，模拟跨代学习与演化。
- 智能体自发形成交流、农业和工具使用等复杂行为。
- 计算资源越多，演化出的复杂性越高，适合研究开放系统中的智能涌现。
人类智能是在地球自然选择与进化过程中产生的。我们探究在计算机中复现这一过程需要什么条件。以往工作多聚焦于低层过程（如物理或化学模拟），而本文采取更直接的方法，旨在培育能跨代积累开放文化与技术的智能体。为此，我们提出 JaxLife：一个基于深度神经网络参数化的具身智能体人工生命模拟器，其运行于包含可编程系统的表达性环境中。首先，我们描述环境并证明其支持有意义的图灵完备计算。随后分析演化出的智能体行为，如原始通信协议、农业实践与工具使用。最后，研究复杂性随计算资源增加的变化规律。我们认为，JaxLife 为在更开放的模拟中研究演化行为迈出了重要一步。代码已开源：https://github.com/luchris429/JaxLife。
原文摘要 · Abstract (English)
Human intelligence emerged through the process of natural selection and evolution on Earth. We investigate what it would take to re-create this process in silico. While past work has often focused on low-level processes (such as simulating physics or chemistry), we instead take a more targeted approach, aiming to evolve agents that can accumulate open-ended culture and technologies across generations. Towards this, we present JaxLife: an artificial life simulator in which embodied agents, parameterized by deep neural networks, must learn to survive in an expressive world containing programmable systems. First, we describe the environment and show that it can facilitate meaningful Turing-complete computation. We then analyze the evolved emergent agents' behavior, such as rudimentary communication protocols, agriculture, and tool use. Finally, we investigate how complexity scales with the amount of compute used. We believe JaxLife takes a step towards studying evolved behavior in more open-ended simulations. Our code is available at https://github.com/luchris429/JaxLife
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。