DM4-ML : Markow Decision Processes

URL to have access to all the codes : https://github.com/ChristopheYe/DM4-ML.git

I. PROJECT'S TITLE

DM4 ML

II. PROJECT DESCRIPTION

The code is written with Python on different Jupyter Notebook The libraries used : import time import io import numpy as np import hiive.mdptoolbox import matplotlib.pyplot as plt from hiive.mdptoolbox import mdp, example from gym.envs.toy_text.frozen_lake import generate_random_map

The goal is to test different algorithms (model-based : Value Iteration and Policy Iteration and model free : Q-learning) on 2 different problems with different size to see the performance and the differences between each of them.

First part : Random Forest

1. Value Iteration
2. Policy Iteration
3. Q-learning

Second part : Frozen Lake

1. Value Iteration
2. Policy Iteration
3. Q-learning

III. HOW TO INSTALL AND RUN THE PROJECT

1. Download Anaconda-Navigator
2. Use a Jupyter Notebook or whatever software which uses python
3. Import all the libraries
4. Run all the different codes in the GitHub