Minimio develops microscopic learned controllers designed for bounded decision-making tasks that are small enough to run on any device. The platform demonstrates these agents navigating diverse maze structures by employing various trained models and spatial algorithms, such as Prim or Kruskal methods.
- Supports grid sizes ranging from 7x7 up to a maximum of 50x50 cells.
- Includes specific model patterns like backtracker, braid, obstacles, and open grids.
- Features interactive controls for adjusting simulation speed and seeding.
- Supports grid sizes ranging from 7x7 up to a maximum of 50x50 cells.
- Includes specific model patterns like backtracker, braid, obstacles, and open grids.
- Features interactive controls for adjusting simulation speed and seeding.
