This course aims to study artificially intelligent agents. It portrays several methods of implementing these agents: from simple reflex agents to utility-based agents as well as learning agents. We first cover greedy and A* search, the implementation of games through the Minimax and Expectimax algorithms, Markov Decision Processes (MDP) and Reinforcement Learning (RL). We then introduce Machine Learning (ML) algorithms with some applications.

Temps présentiel : 30 heures

Charge de travail étudiant : 70 heures

Méthode(s) d'évaluation : Examen final, Examen partiel, Travail personnel