Reinforcement Learning (RL)

In this repository, I share my codes while studying reinforcement learning and attempting to implement the majority of algorithms introduced in the Sutton and Barto textbook.

Table of Contents

• Introduction
• Algorithms
• Usage

Introduction

This repository contains implementations of various reinforcement learning algorithms, following the approaches described in the book "Reinforcement Learning: An Introduction" by Sutton and Barto. The goal is to provide a comprehensive set of examples to help others understand and apply these concepts.

Algorithms

Dynamic Programming

• Policy Iteration
• Value Iteration

Model-Free Methods

• Monte Carlo Methods
• Temporal-Difference Learning
  • SARSA
  • Q-Learning
• Actor-Critic Methods
  • A2C (Advantage Actor-Critic)

Usage

Clone the repository and explore the notebooks to understand the implementation details. Each folder contains a set of Jupyter notebooks with detailed explanations and code.

git clone https://github.com/alirezaghl/RL.git
cd RL