Parameter
- 416 Seiten
- 15 Lesestunden
Mehr zum Buch
This introduction to deep reinforcement learning (deep RL) merges theory and practice, focusing on how artificial agents tackle sequential decision-making problems. Over the past decade, deep RL has made significant strides in various domains, including games like Go and DotA 2, as well as robotics. The text begins with foundational intuition, progresses through the theoretical underpinnings of deep RL algorithms, and includes practical implementation guidance using the companion software library, SLM Lab. Key topics covered include policy- and value-based algorithms such as REINFORCE, SARSA, DQN, Double DQN, and Prioritized Experience Replay (PER), as well as combined algorithms like Actor-Critic and Proximal Policy Optimization (PPO). The book also addresses the parallelization of algorithms, both synchronously and asynchronously, and provides insights into running algorithms in SLM Lab, detailing the practical aspects of implementing deep RL successfully. Readers can explore benchmark results with optimized hyperparameters and learn about the design of deep RL environments. This resource is tailored for computer science students and software engineers with a basic understanding of machine learning and proficiency in Python. Additionally, registering for the book offers easy access to downloads, updates, and corrections.
Buchkauf
Foundations of Deep Reinforcement Learning, Wah Loon Keng, Laura Harding Graesser
- Sprache
- Erscheinungsdatum
- 2019
- Einband
- (Paperback)
Keiner hat bisher bewertet.
- Titel
- Foundations of Deep Reinforcement Learning
- Untertitel
- Theory and Practice in Python
- Sprache
- Englisch
- Autor*innen
- Wah Loon Keng, Laura Harding Graesser
- Verlag
- Pearson
- Erscheinungsdatum
- 2019
- Einband
- Paperback
- Seitenzahl
- 416
- ISBN10
- 0135172381
- ISBN13
- 9780135172384
- Reihe
- Schlagwörter
- Technologie & Industrie, Computer & Internet, USA, Künstliche Intelligenz, Datenbanken, Maschinelles Lernen
- Beschreibung
- This introduction to deep reinforcement learning (deep RL) merges theory and practice, focusing on how artificial agents tackle sequential decision-making problems. Over the past decade, deep RL has made significant strides in various domains, including games like Go and DotA 2, as well as robotics. The text begins with foundational intuition, progresses through the theoretical underpinnings of deep RL algorithms, and includes practical implementation guidance using the companion software library, SLM Lab. Key topics covered include policy- and value-based algorithms such as REINFORCE, SARSA, DQN, Double DQN, and Prioritized Experience Replay (PER), as well as combined algorithms like Actor-Critic and Proximal Policy Optimization (PPO). The book also addresses the parallelization of algorithms, both synchronously and asynchronously, and provides insights into running algorithms in SLM Lab, detailing the practical aspects of implementing deep RL successfully. Readers can explore benchmark results with optimized hyperparameters and learn about the design of deep RL environments. This resource is tailored for computer science students and software engineers with a basic understanding of machine learning and proficiency in Python. Additionally, registering for the book offers easy access to downloads, updates, and corrections.