This repository contains a collection of machine learning projects.
A desktop application that recognizes handwritten digits. It features a GUI built with PySide6 where users can draw a digit, which is then classified by a Convolutional Neural Network (CNN) trained on the MNIST dataset using PyTorch.
An implementation of various AI agents to play Connect 4. This project includes a gymnasium-compatible game environment and features agents using Minimax with alpha-beta pruning and Monte Carlo Tree Search (MCTS). You can play against the agents or have them compete against each other.
A project focused on reinforcement learning, specifically implementing a Deep Q-Learning (DQN) algorithm. The env.py file sets up the environment for this task.