Learning to Play

1. Front Matter

   Pages i-xiii

   PDF

2. Introduction

   • Aske Plaat

   Pages 1-7

3. Intelligence and Games

   • Aske Plaat

   Pages 9-42

4. Reinforcement Learning

   • Aske Plaat

   Pages 43-69

5. Heuristic Planning

   • Aske Plaat

   Pages 71-112

6. Adaptive Sampling

   • Aske Plaat

   Pages 113-134

7. Function Approximation

   • Aske Plaat

   Pages 135-194

8. Self-Play

   • Aske Plaat

   Pages 195-232

9. Conclusion

   • Aske Plaat

   Pages 233-254

10. Back Matter

    Pages 255-330

    PDF

In this textbook the author takes as inspiration recent breakthroughs in game playing to explain how and why deep reinforcement learning works. In particular he shows why two-person games of tactics and strategy fascinate scientists, programmers, and game enthusiasts and unite them in a common goal: to create artificial intelligence (AI). 

After an introduction to the core concepts, environment, and communities of intelligence and games, the book is organized into chapters on reinforcement learning, heuristic planning, adaptive sampling, function approximation, and self-play. The author takes a hands-on approach throughout, with Python code examples and exercises that help the reader understand how AI learns to play. He also supports the main text with detailed pointers to online machine learning frameworks, technical details for AlphaGo, notes on how to play and program Go and chess, and a comprehensive bibliography.


The content is class-tested and suitable for advanced undergraduate and graduate courses on artificial intelligence and games. It's also appropriate for self-study by professionals engaged with applications of machine learning and with games development. Finally it's valuable for any reader engaged with the philosophical implications of artificial and general intelligence, games represent a modern Turing test of the power and limitations of AI.

• Deep Learning
• Machine Learning
• Reinforcement Learning
• Artificial Intelligence
• Computational Intelligence
• Evolutionary Computing
• Heuristics
• Games
• AlphaGo
• Go
• Markov Decision Processes
• Adaptive Sampling

• Leiden Institute of Advanced Computer Science, Leiden University, Leiden, The Netherlands

  Aske Plaat

Prof. Aske Plaat is Professor of Data Science at Leiden University and scientific director of the Leiden Institute of Advanced Computer Science (LIACS). He is co-founder of the Leiden Centre of Data Science (LCDR) and initiated the SAILS stimulation program. His research interests include reinforcement learning, scalable combinatorial reasoning algorithms, games and self-learning systems.

Policies and ethics