Abstract
In this chapter, we will do a deep dive into Q-learning combined with function approximation using neural networks. Q-learning in the context of deep learning using neural networks is also known as Deep Q Networks (DQN). We will first summarize what we have talked about so far with respect to Q-learning. We will then look at code implementations of DQN on simple problems followed by training an agent to play Atari games. Following this, we will extend our knowledge by looking at various modifications that can be done to DQN to improve the learning, including some very recent and state-of-the-art approaches. Some of these approaches may involve a bit of math to understand the rationale for these approaches. However, we will try to keep the math to a minimum and include just the required details to appreciate the background and reasoning. All the examples in this chapter will be coded using either the PyTorch or TensorFlow library. Some code walk-throughs will have the code for both PyTorch and TensorFlow, while others will be discussed using only PyTorch.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
- 4.
- 5.
- 6.
- 7.
- 8.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2021 Nimish Sanghi
About this chapter
Cite this chapter
Sanghi, N. (2021). Deep Q-Learning. In: Deep Reinforcement Learning with Python. Apress, Berkeley, CA. https://doi.org/10.1007/978-1-4842-6809-4_6
Download citation
DOI: https://doi.org/10.1007/978-1-4842-6809-4_6
Published:
Publisher Name: Apress, Berkeley, CA
Print ISBN: 978-1-4842-6808-7
Online ISBN: 978-1-4842-6809-4
eBook Packages: Professional and Applied ComputingApress Access BooksProfessional and Applied Computing (R0)