I've used AI (CNNs, behavioral cloning, reinforcement learning etc) for several projects. In this page, I only list projects that were part of the Artificial Intelligence course at KTH. More information can be found here.
2D, 4x4 Tic Tac Toe: The task was to find the best possible move for player X given a particular state of the game using alfa-beta pruning on the minimax algorithm's search tree.
3D, 4x4x4 Tic Tac Toe: The task was to find the best possible move for player X given a particular state of the game using again alfa-beta-pruning applied on the minimax algorithm's search tree.
Checkers: In this task, our goal was to implement a strategy that allows our program to win (or not lose) as often as possible, using alpha-beta pruning.
Duckhunt: In this task I classified the birds and based on the probability distribution of the classification of the bird, decide to shoot it or not, guessed the type of each bird based on the observations and revealed the correct type of the bird based on a HMM (Hidden Markov Model).