View preset
A policy in the making
Seeded Q-learning with editable learning rate and discount.
Preparing the preview…
Made to be adapted.
The agent starts at the lower-left corner and aims for the glowing goal. Walls block movement. Reaching the goal gives +1, hazards end the episode with −0.7, and every other move costs 0.025.
Interactive mathematical model. Use the controls to explore the mechanism; this is not a benchmark result.
- Export formats
- PNG / HTML
- Editable in Studio
- Explanation, appearance, and model inputs
- Access
- Free with attribution. No account needed.
- Reference
- Read the source