Original Summary

Full-connectome-inspired reinforcement learning with the male Drosophila connectome. Sparse CUDA simulation, visual Mario control, connectome-based sensorimotor mapping, policy-gradient learning, and reproducible Colab experiments.

  • 情报分类：综合情报
  • 分类依据：内容未命中明确的垂直分类规则，归入综合情报
  • 信息来源：GitHub · AI 新项目
  • 发布时间：2026/9/24 09:14:21