CodeUtility
Making your developer's life easier!
Back to challenges

AI learning path

Code classical AI and reinforcement learning in C#

8 challenges on how machines search, play games and learn from rewards: A* pathfinding, minimax and alpha-beta, genetic algorithms, Markov chains, multi-armed bandits, value iteration and Q-learning. Solve them in order in C#; each one runs in your browser with instant tests and an AI review.

Start the first challenge
  1. 1

    Search, games and evolution

    A* pathfinding, minimax, alpha-beta pruning and genetic algorithms.

    0/4
    1. 1 A* Search on a Weighted Grid Medium Solve in C#
    2. 2 Minimax Tic-Tac-Toe Medium Solve in C#
    3. 3 Alpha-Beta Pruning Medium Solve in C#
    4. 4 One Generation of a Genetic Algorithm Medium Solve in C#
  2. 2

    Chance and exploration

    Markov chains and the exploration-exploitation trade-off.

    0/2
    1. 1 Markov Chain State Distribution Easy Solve in C#
    2. 2 Epsilon-Greedy Multi-Armed Bandit Easy Solve in C#
  3. 3

    Reinforcement learning

    Value iteration and Q-learning.

    0/2
    1. 1 Value Iteration Medium Solve in C#
    2. 2 Q-Learning Updates Medium Solve in C#