Q-learning

Training an agent using Q-Learning algorithm to play flappy bird game which we made before using PyOpenGL python library.

This project adopts Reinforcement Learning to solve a variant of the stochastic VRP, where customers are highly variable, demands are stochastic, and vehicles have a duration limit.

Solution of Cliff Walking problem with different variants of Q-learning and SARSA algorithms.

C++ high-performance gym environment framework

Proyecto final del Grado Superior de Desarrollo de Aplicaciones Multiplataforma

Machine Learning (ML) algorithm for the resource allocation problems in the Low Power Wide Area Network (LPWAN).

Application of deep Q-Learning to play Snake.

Project for the Machine Learning course, A.Y. 2015/2016, Politecnico di Milano