# ehennis/ReinforcementLearning

Repository for my CS6460 Education Technology Project
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.
Milestone 1
Milestone 2
.gitignore
01-RLBasics.ipynb
02-QLearning.ipynb
03-DoubleQLearning.ipynb
04-NeuralNetworks.ipynb
05-DQN.ipynb
06-DDQN.ipynb
BlankGraph.png
Graph-And.png
IowaCodeCamp.pptx
Notes.txt
References.txt
basic.py
doubleq.py
qlearning.py

# Introduction to Reinforcement Learning

Author: Evan Hennis
Summary: This repository is for CS6460 Education Technology Fall 2018. My project will be to create content that will teach reinforcement learning. I will start with the basics of RL (Decision making, MDP, Policy Iteration, Value Iteration) and then work through Q-Learning and all of its enhancements (Double Q-Learning, DQN, and Double DQN).
Repository Instructions: To use this repository you will need to find the section you want to learn and open the notebook associated with it.

## Section 1: Reinforcement Learning Basics

Topics Covered: Decision Making, Markov Decision Process, Policy Iteration, Value Iteration, Deterministic Movements, and Stochastic Movements. ??Maybe reference discrete and continuous environments here??
Notebook:: 01-RLBasics.ipynb

## Section 2: Q-Learning

Topics Covered: Q-Learning, Discrete Environments, and Continuous Environments
Notebook: 02-QLearning.ipynb

## Section 3: Double Q-Learning

Notebook: 03-DoubleQLearning.ipynb

## Section 4: Neural Networks

Notebook: 04-NeuralNetworks.ipynb

## Section 5: DQN

Notebook: 05-DQN.ipynb

## Section 6: Double DQN

Notebook: 06-DDQN.ipynb

# Current Environment Setup

Windows 10
Python 3.6.1
Anaconda3 4.4.0
TensorFlow 1.2.0
Keras 2.0.5
Gym (OpenAI) 0.9.1
NumPy 1.12.1
MatPlotLib 2.0.2
Jupyter Notebooks