Educational repository exploring generative models from classic to modern approaches,

A Reinforcement Learning course with classic examples of agents trained on gym environments.

Branches algorithm, fast AO* search for optimal sparse Decision Trees.

Online Learning of Decision Trees via Monte Carlo Tree Search with a Thompson Sampling policy

Deep learning (vision, nlp, reinforcement) home works (MVA-CentraleSupelec)

Large scale and distributed computing optimization course (MVA-CentraleSupelec)

Constituency parser for French based on probabilistic context free grammar and CYK algorithm

Probabilistic graphical models home works (MVA - ENS Cachan)

Reinforcement learning homeworks (MVA)