Artificial Intelligence: final assessment
This covers the whole course. Take it after the last module.
Final quiz
Practical assessment: Build an agent for a grid world
Without using hints, write a program that reads a grid map and solves it three ways: the shortest path with A*, the optimal policy when moves slip with value iteration, and a learned policy with Q-learning.
- A* uses an admissible heuristic and reports the cells expanded
- Value iteration stops when the largest change is tiny and prints the policy
- Q-learning uses ε-greedy exploration with a fixed random seed
- The program prints the three results on the map and compares the learned policy with the optimal one
- Unreachable goals and maps without a goal are reported clearly
Final project
A robot that plans, tracks and learns: Build a grid-world robot that finds paths with A*, keeps track of its position from noisy sensor readings, plans under slippery moves with value iteration, and learns the same task with Q-learning.
How it is evaluated
- Correctness: paths are shortest, policies are optimal, and the comparison is accurate
- Understanding: you can explain each algorithm's update rule and why it works
- Design: search, planning and learning are separate, tested functions
- Evidence: the report includes numbers such as cells expanded and episodes needed
To complete this course
- Score at least 70% on the final quiz
- Solve the beginner and intermediate exercises in every lesson
- Finish the final project and check it against the evaluation criteria