Book Image

Deep Reinforcement Learning with Python - Second Edition

By : Sudharsan Ravichandiran
Book Image

Deep Reinforcement Learning with Python - Second Edition

By: Sudharsan Ravichandiran

Overview of this book

With significant enhancements in the quality and quantity of algorithms in recent years, this second edition of Hands-On Reinforcement Learning with Python has been revamped into an example-rich guide to learning state-of-the-art reinforcement learning (RL) and deep RL algorithms with TensorFlow 2 and the OpenAI Gym toolkit. In addition to exploring RL basics and foundational concepts such as Bellman equation, Markov decision processes, and dynamic programming algorithms, this second edition dives deep into the full spectrum of value-based, policy-based, and actor-critic RL methods. It explores state-of-the-art algorithms such as DQN, TRPO, PPO and ACKTR, DDPG, TD3, and SAC in depth, demystifying the underlying math and demonstrating implementations through simple code examples. The book has several new chapters dedicated to new RL techniques, including distributional RL, imitation learning, inverse RL, and meta RL. You will learn to leverage stable baselines, an improvement of OpenAI’s baseline library, to effortlessly implement popular RL algorithms. The book concludes with an overview of promising approaches such as meta-learning and imagination augmented agents in research. By the end, you will become skilled in effectively employing RL and deep RL in your real-world projects.
Table of Contents (22 chapters)
Other Books You May Enjoy

The architecture of CNNs

Figure 7.41 shows the architecture of a CNN:

Figure 7.41: Architecture of CNN

As you will notice, first we feed the input image to the convolutional layer, where we apply the convolution operation to extract important features from the image and create the feature maps. We then pass the feature maps to the pooling layer, where the dimensions of the feature maps will be reduced.

As shown in the previous diagram, we can have multiple convolutional and pooling layers, and we should also note that the pooling layer does not necessarily have to be there after every convolutional layer; there can be many convolutional layers followed by a pooling layer.

So, after the convolutional and pooling layers, we flatten the resultant feature maps and feed it to a fully connected layer, which is basically a feedforward neural network that classifies the given input image based on the feature maps.

Now that we have learned how CNNs work, in the next...