Rough Cuts are manuscripts that are developed but not yet published, available through Safari. Rough Cuts provide you access to the very latest information on a given topic and offer you the opportunity to interact with the author to influence the final publication.
Also available in other formats.
This is the Rough Cut version of the printed book.
The Contemporary Introduction to Deep Reinforcement Learning that Combines Theory and Practice
Deep reinforcement learning (deep RL) combines deep learning and reinforcement learning, in which artificial agents learn to solve sequential decision-making problems. In the past decade deep RL has achieved remarkable results on a range of problems, from single and multiplayer games—such as Go, Atari games, and DotA 2—to robotics.
Foundations of Deep Reinforcement Learning is an introduction to deep RL that uniquely combines both theory and implementation. It starts with intuition, then carefully explains the theory of deep RL algorithms, discusses implementations in its companion software library SLM Lab, and finishes with the practical details of getting deep RL to work.
AcknowledgmentsAbout the Authors
Chapter 1: Introduction to Reinforcement Learning
Part I: Policy-Based and Value-Based Algorithms
Chapter 2: Policy Gradient
Chapter 3: State Action Reward State Action
Chapter 4: Deep Q-Networks
Chapter 5: Improving Deep Q-Networks
Part II: Combined Methods
Chapter 6: Advantage Actor-Critic
Chapter 7: Proximal Policy Optimization
Chapter 8: Parallelization Methods
Chapter 9: Algorithm Summary
Part III: Practical Tips
Chapter 10: Getting Reinforcement Learning to Work
Chapter 11: SLM Lab
Chapter 12: Network Architectures
Chapter 13: Hardward
Chapter 14: Environment Design
Appendix A: Deep Reinforcement Learning Timeline
Appendix B: Example Environments