---
title: Reinforcement Learning
description: This area of machine learning focuses on how software agents ought to take actions in an environment to maximize cumulative rewards. Learners will understand how to design decision-making models using Markov decision processes and Q-learning algorithms.
category: programming-tech
subcategory: artificial-intelligence
difficulty: beginner, intermediate, advanced
url: /subject/reinforcement-learning
---

# Reinforcement Learning

This area of machine learning focuses on how software agents ought to take actions in an environment to maximize cumulative rewards. Learners will understand how to design decision-making models using Markov decision processes and Q-learning algorithms.

## Available Resources

1 Books • 3 Courses • 3 Websites

## Websites

### 1. RL Baselines3 Zoo

A training framework built on Stable-Baselines3, with tuned hyperparameters and 200+ pretrained agents for Atari, MuJoCo, and robotics tasks. Running its scripts teaches you how to train, evaluate, and benchmark RL agents reproducibly.

**Difficulty:** Beginner | **Price:** Free

**Link:** https://github.com/DLR-RM/rl-baselines3-zoo

**Tags:** stable-baselines3, rl-frameworks, pretrained-agents, hyperparameter-tuning, benchmarking

### 2. OpenAI Spinning Up

An OpenAI educational resource covering deep RL theory, key papers, and simplified implementations of VPG, TRPO, PPO, DDPG, TD3, and SAC. After working through it you can read RL papers and implement policy-gradient algorithms yourself.

**Difficulty:** Beginner | **Price:** Free

**Link:** https://spinningup.openai.com/en/latest/

**Tags:** deep-rl, policy-gradients, openai, algorithm-implementations, rl-fundamentals

### 3. Sutton & Barto Book (Free PDF)

Richard Sutton's page hosting the complete second-edition draft of the standard RL textbook, plus code and errata. It covers bandits, Markov decision processes, temporal-difference learning, function approximation, and policy gradients, giving you the field's theoretical foundation.

**Difficulty:** Beginner | **Price:** Free

**Link:** https://incompleteideas.net/book/the-book-2nd.html

**Tags:** textbook, rl-theory, temporal-difference-learning, markov-decision-processes, function-approximation

## Courses

### 1. CS 285: Deep Reinforcement Learning

Learn deep reinforcement learning with Sergey Levine's CS 285 course. Explore cutting-edge algorithms and build intelligent agents!

**Difficulty:** Advanced | **Price:** Free

**Link:** https://rail.eecs.berkeley.edu/deeprlcourse/

**Tags:** deep-rl, policy-gradients, model-based-rl, berkeley, graduate-course

### 2. Deep Reinforcement Learning

Learn Deep Reinforcement Learning with Simon Osindero! Master RL algorithms & build intelligent agents in this comprehensive course.

**Difficulty:** Beginner | **Price:** Free

**Link:** https://huggingface.co/learn/deep-rl-course/en/unit0/introduction

**Tags:** deep-rl, hugging-face, stable-baselines3, hands-on-course, rl-agents

### 3. DeepMind x UCL | Introduction to Reinforcement Learning 2015

Learn reinforcement learning from David Silver's comprehensive course! Master algorithms & build intelligent agents.

**Difficulty:** Intermediate | **Price:** Free

**Link:** https://www.youtube.com/playlist?list=PLqYmG7hTraZDM-OYHWgPebj2MfCFzFObQ

**Tags:** rl-fundamentals, markov-decision-processes, dynamic-programming, temporal-difference-learning, lecture-series

## Books

### 1. Deep Reinforcement Learning Hands-On

**Author:** Maxim Lapan

A PyTorch-based walkthrough of deep RL methods, from deep Q-networks and value iteration through policy gradients, TRPO, and AlphaGo Zero, applied to Atari, stock trading, and chatbots. You finish able to implement and debug these agents.

**Difficulty:** Intermediate | **Language:** English | **Price:** Paid

**Link:** https://www.amazon.com/dp/1788834240?tag=edmonddante07-20

**Tags:** books, technology-computer-science, ai-ml

---

*This content is part of Dantes.io - Your Treasure Map to Knowledge*

*Curated by humans at Dantes.io. Personal study use welcome; republishing this curation requires permission (team@dantes.io).*

View this page online: https://dantes.io/subject/reinforcement-learning