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


We started off the chapter by understanding biological and artificial neurons. Then we learned about ANNs and their layers. We learned different types of activation functions and how they are used to introduce nonlinearity in the network.

Later, we learned about the forward and backward propagation in the neural network. Next, we learned how to implement an ANN. Moving on, we learned about RNNs and how they differ from feedforward networks. Next, we learned about the variant of the RNN called LSTM. Going forward, we learned about CNNs, how they use different types of layers, and the architecture of CNNs in detail.

At the end of the chapter, we learned about an interesting algorithm called GAN. We understood the generator and discriminator component of GAN and we also explored the architecture of GAN in detail. Followed by that, we examined the loss function of GAN in detail.

In the next chapter, we will learn about one of the most popularly used deep...