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 the chapter by understanding how distributional reinforcement learning works. We learned that in distributional reinforcement learning, instead of selecting an action based on the expected return, we select the action based on the distribution of return, which is often called the value distribution or return distribution.

Next, we learned about the categorical DQN algorithm, also known as C51, where we feed the state and support of the distribution as the input and the network returns the probabilities of the value distribution. We also learned how the projection step matches the support of the target and predicted the value distribution so that we can apply the cross entropy loss.

Going ahead, we learned about quantile regression DQNs, where we feed the state and also the equally divided cumulative probabilities as input to the network and it returns the support value of the distribution.

At the end of the chapter, we learned about how D4PG...