JaxLife: An Open-Ended Agentic Simulator
This work addresses the challenge of evolving open-ended cultural and technological accumulation in AI agents, representing an incremental step in artificial life simulations.
The paper tackles the problem of recreating human-like intelligence through evolution in silico by developing JaxLife, an artificial life simulator where neural network-based agents evolve in a programmable world, resulting in emergent behaviors like communication, agriculture, and tool use, with complexity scaling with compute.
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