Reinforcement Learning Textbook

TL;DR

This textbook provides a comprehensive overview of modern deep reinforcement learning algorithms, explaining their theoretical foundations, differences, and practical applications across various domains.

Contribution

It offers a unified, proof-based explanation of reinforcement learning algorithms, highlighting their differences and underlying principles, which is a novel educational resource.

Findings

Unified notation for algorithms

Detailed theoretical explanations with proofs

Comparison of algorithm types

Abstract

This textbook covers principles behind main modern deep reinforcement learning algorithms that achieved breakthrough results in many domains from game AI to robotics. All required theory is explained with proofs using unified notation and emphasize on the differences between different types of algorithms and the reasons why they are constructed the way they are.