This project simulates a real-world delivery task where an AI agent must reach a goal position efficiently.
Move the agent from start (0) to goal position.
- 0 → Move Left
- 1 → Move Right
- position
- goal
- +1 → Reached goal
- -0.1 → Each step
- Easy → goal = 3
- Medium → goal = 5
- Hard → goal = 10
python test.py