PROJECT FILM / ZONGO MAQUTU
A Python grid-world learning history
Watch a recorded state history from a Python Q-learning grid-world experiment with rewards and obstacles.
What the film shows
- A grid defines the agent’s possible states.
- Rewards and obstacles shape the learning problem.
- The visualization advances through a recorded learning history.
Behind the demonstration
A historical repository animation shortened for playback. The associated Field Note distinguishes Q-learning from the separate value-iteration experiment.
Built and documented by Zongo Maqutu. Read the Field Note for the implementation, architecture and limitations.