## Foundations of Deep Reinforcement Learning: Theory and Practice in PythonThe 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. 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. Foundations of Deep Reinforcement Learning This guide is ideal for both computer science students and software engineers who are familiar with basic machine learning concepts and have a working understanding of Python. - Understand each key aspect of a deep RL problem
- Explore policy- and value-based algorithms, including REINFORCE, SARSA, DQN, Double DQN, and Prioritized Experience Replay (PER)
- Delve into combined algorithms, including Actor-Critic and Proximal Policy Optimization (PPO)
- Understand how algorithms can be parallelized synchronously and asynchronously
- Run algorithms in SLM Lab and learn the practical implementation details for getting deep RL to work
- Explore algorithm benchmark results with tuned hyperparameters
- Understand how deep RL environments are designed
Register your book for convenient access to downloads, updates, and/or corrections as they become available. See inside book for details. |

### What people are saying - Write a review

User Review - Flag as inappropriate

This book is good for graduate students who are beginners in deep reinforcement learning and want to grasp both the practical and theoretical understanding of deep reinforcement learning. Unlike other books, this book is laced with practical illustration of mathematical equations and how to implement the algorithms with software programming. It is also a refresher book for experts in the field.

### Contents

PolicyBased and ValueBased Algorithms | |

SARSA | |

Deep QNetworks DQN | |

Improving | |

Combined Methods | |

Parallelization Methods | |

Hardware | |

Environment Design | |

Actions | |

Rewards | |

Transition Function | |

Epilogue | |

B Example Environments | |

References | |

### Other editions - View all

Deep Reinforcement Learning in Python: A Hands-On Introduction Laura Harding Graesser,Wah Loon Keng No preview available - 2019 |

### Common terms and phrases

action advantage agent algorithm applied Atari batch calculate changes Chapter Click combined complex components consider contains continuous debugging deep RL discrete discussed distribution effective elements environment episode Equation estimate example experiences exploration Figure four frame fully function given global human hyperparameters implementation import Initialize input known layers look loss means memory method moving multiple neural network objective observed OpenAI optimal output parallelization parameters performance pixels play policy gradient position possible practice probability problem produce provides Q-value Reinforcement Learning Replay represent requires reward sampling SARSA shown shows signal simple single SLM Lab solve space spec file specific standard step stored task tensor transition trial typically unit update values view code image