Ravichandiran Hands-On Reinforcement Learning with Python

Master reinforcement and deep reinforcement learning using OpenAI Gym and TensorFlow
1. Auflage 2018
ISBN: 978-1-78883-691-3
Verlag: De Gruyter
Format: EPUB
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)

E-Book, Englisch, 318 Seiten

No detailed description available for "Hands-On Reinforcement Learning with Python".

Autoren/Hrsg.

Ravichandiran, Sudharsan

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Theoretische Informatik
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Neuronale Netzwerke

Inhaltsverzeichnis

Table of Contents - Introduction to Reinforcement Learning
- Getting started with OpenAI and Tensorflow
- Markov Decision process and Dynamic Programming
- Gaming with Monte Carlo Tree Search
- Temporal Difference Learning
- Multi-Armed Bandit Problem
- Deep Learning Fundamentals
- Deep Learning and Reinforcement
- Playing Doom With Deep Recurrent Q Network
- Asynchronous Advantage Actor Critic Network
- Policy Gradients and Optimization
- Capstone Project – Car Racing using DQN
- Current Research and Next Steps

Über Autor(innen)

Ravichandiran Sudharsan:

Sudharsan Ravichandiran is a data scientist and artificial intelligence enthusiast. He holds a Bachelors in Information Technology from Anna University. His area of research focuses on practical implementations of deep learning and reinforcement learning including natural language processing and computer vision. He is an open-source contributor and loves answering questions on Stack Overflow.