Simulate Taxi rides in the city.

T-AIA-902 project from MSC Pro Epitech's course. It's about an AI project to learn discover reinforcement learning, its algorithms and how to tweak params to make an agent learn how to play a simple game. This project is fully built in Python and designed as best as it can to allow its extension with new algorithms.

This is a project of reinforcement learning which contains two different environments. The first environment is the taxi driver problem in 4x4 space with the simple Q-learning update rule. In this task, we compared the performance of the e-greedy policy and Boltzmann policy. As a second environment, we chose the LunarLander from the open gym. Fo…