Deep Reinforcement Learning in Action, Video Edition

Deep Reinforcement Learning in Action, Video Edition

by Brandon Brown, Alexander Zai
Released March 2020
Publisher(s): Manning Publications
ISBN: None

Watch it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Video description

In Video Editions the narrator reads the book while the content, figures, code listings, diagrams, and text appear on the screen. Like an audiobook that you can also watch as a video.

Humans learn best from feedback—we are encouraged to take actions that lead to positive results while deterred by decisions with negative consequences. This reinforcement process can be applied to computer programs allowing them to solve more complex problems that classical programming cannot. Deep Reinforcement Learning in Action teaches you the fundamental concepts and terminology of deep reinforcement learning, along with the practical skills and techniques you’ll need to implement it into your own projects.

About the Technology
Deep reinforcement learning AI systems rapidly adapt to new environments, a vast improvement over standard neural networks. A DRL agent learns like people do, taking in raw data such as sensor input and refining its responses and predictions through trial and error.

About the Book
Deep Reinforcement Learning in Action teaches you how to program AI agents that adapt and improve based on direct feedback from their environment. In this example-rich tutorial, you’ll master foundational and advanced DRL techniques by taking on interesting challenges like navigating a maze and playing video games. Along the way, you’ll work with core algorithms, including deep Q-networks and policy gradients, along with industry-standard tools like PyTorch and OpenAI Gym.

What's Inside

  • Building and training DRL networks
  • The most popular DRL algorithms for learning and problem solving
  • Evolutionary algorithms for curiosity and multi-agent learning
  • All examples available as Jupyter Notebooks


About the Reader
For readers with intermediate skills in Python and deep learning.

About the Author
Alexander Zai is a machine learning engineer at Amazon AI. Brandon Brown is a machine learning and data analysis blogger.

Quotes
A thorough introduction to reinforcement learning. Fun to read and highly relevant.
- Helmut Hauschild, PharmaTrace

An essential read for anyone who wants to master deep reinforcement learning.
- Kalyan Reddy, ArisGlobal

If you ever wondered what the theory is behind AI/ML and reinforcement learning, and how you can apply the techniques in your own projects, then this book is for you.
- Tobias Kaatz, OpenText

I highly recommend this book to anyone who aspires to master the fundamentals of DRL and seeks to follow a research or development career in this exciting field.
- Al Rahimi, Amazon

Publisher resources

View/Submit Errata

Table of contents

  1. Part 1. Foundations
  2. Chapter 1. What is reinforcement learning?
  3. Chapter 1. Reinforcement learning
  4. Chapter 1. Dynamic programming versus Monte Carlo
  5. Chapter 1. The reinforcement learning framework
  6. Chapter 1. What can I do with reinforcement learning?
  7. Chapter 1. Why deep reinforcement learning?
  8. Chapter 1. Our didactic tool: String diagrams
  9. Chapter 1. What’s next?
  10. Chapter 1. Summary
  11. Chapter 2. Modeling reinforcement learning problems: Markov decision processes
  12. Chapter 2. Solving the multi-arm bandit
  13. Chapter 2. Applying bandits to optimize ad placements
  14. Chapter 2. Building networks with PyTorch
  15. Chapter 2. Solving contextual bandits
  16. Chapter 2. The Markov property
  17. Chapter 2. Predicting future rewards: Value and policy functions
  18. Chapter 2. Summary
  19. Chapter 3. Predicting the best states and actions: Deep Q-networks
  20. Chapter 3. Navigating with Q-learning
  21. Chapter 3. Preventing catastrophic forgetting: Experience replay
  22. Chapter 3. Improving stability with a target network
  23. Chapter 3. Review
  24. Chapter 3. Summary
  25. Chapter 4. Learning to pick the best policy: Policy gradient methods
  26. Chapter 4. Reinforcing good actions: The policy gradient algorithm
  27. Chapter 4. Working with OpenAI Gym
  28. Chapter 4. The REINFORCE algorithm
  29. Chapter 4. Summary
  30. Chapter 5. Tackling more complex problems with actor-critic methods
  31. Chapter 5. Distributed training
  32. Chapter 5. Advantage actor-critic
  33. Chapter 5. N-step actor-critic
  34. Chapter 5. Summary
  35. Part 2. Above and beyond
  36. Chapter 6. Alternative optimization methods: Evolutionary algorithms
  37. Chapter 6. Reinforcement learning with evolution strategies
  38. Chapter 6. A genetic algorithm for CartPole
  39. Chapter 6. Pros and cons of evolutionary algorithms
  40. Chapter 6. Evolutionary algorithms as a scalable alternative
  41. Chapter 6. Summary
  42. Chapter 7. Distributional DQN: Getting the full story
  43. Chapter 7. Probability and statistics revisited
  44. Chapter 7. The Bellman equation
  45. Chapter 7. Distributional Q-learning
  46. Chapter 7. Comparing probability distributions
  47. Chapter 7. Dist-DQN on simulated data
  48. Chapter 7. Using distributional Q-learning to play Freeway
  49. Chapter 7. Summary
  50. Chapter 8. Curiosity-driven exploration
  51. Chapter 8. Inverse dynamics prediction
  52. Chapter 8. Setting up Super Mario Bros.
  53. Chapter 8. Preprocessing and the Q-network
  54. Chapter 8. Setting up the Q-network and policy function
  55. Chapter 8. Intrinsic curiosity module
  56. Chapter 8. Alternative intrinsic reward mechanisms
  57. Chapter 8. Summary
  58. Chapter 9. Multi-agent reinforcement learning
  59. Chapter 9. Neighborhood Q-learning
  60. Chapter 9. The 1D Ising model
  61. Chapter 9. Mean field Q-learning and the 2D Ising model
  62. Chapter 9. Mixed cooperative-competitive games
  63. Chapter 9. Summary
  64. Chapter 10. Interpretable reinforcement learning: Attention and relational models
  65. Chapter 10. Relational reasoning with attention
  66. Chapter 10. Implementing self-attention for MNIST
  67. Chapter 10. Multi-head attention and relational DQN
  68. Chapter 10. Double Q-learning
  69. Chapter 10. Training and attention visualization
  70. Chapter 10. Summary
  71. Chapter 11. In conclusion: A review and roadmap
  72. Chapter 11. The uncharted topics in deep reinforcement learning
  73. Chapter 11. The end
  74. Appendix. Mathematics, deep learning, PyTorch
  75. Appendix. Calculus
  76. Appendix. Deep learning
  77. Appendix. PyTorch

Product information

  • Title: Deep Reinforcement Learning in Action, Video Edition
  • Author(s): Brandon Brown, Alexander Zai
  • Release date: March 2020
  • Publisher(s): Manning Publications
  • ISBN: None