DQN agent with e-greedy / softmax policy, experience replay and target network.

Q-value iteration algorithm & ON-policy vs OFF-policy learning, introducing SARSA and Q-learning algorithms in the Stochastic Windy Grid environment

AI agents for Trackmania using the TMRL package. Implemented DDPG, PPO, and used two SAC algorithms (with one or two critics) to train cars to navigate custom-built tracks.

The objective of this project is to create a deep learning model trained to answer specific questions from various domains. This type of model is generally called a "chatbot".

This project consists in using machine learning to analyze the factors that affect wine quality and in building a model for predicting it. The model was tested on unseen wines to evaluate its accur…