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 what TD learning is and how it takes advantage of both DP and the MC method. We learned that, just like DP, TD learning bootstraps, and just like the MC method, TD learning is a model-free method.

Later, we learned how to perform a prediction task using TD learning, and then we looked into the algorithm of the TD prediction method.

Going forward, we learned how to use TD learning for a control task. First, we learned about the on-policy TD control method called SARSA, and then we learned about the off-policy TD control method called Q learning. We also learned how to find the optimal policy in the Frozen Lake environment using the SARSA and Q learning methods.

We also learned the difference between SARSA and Q learning methods. We understood that SARSA is an on-policy algorithm, meaning that we use a single epsilon-greedy policy to select an action in the environment and also to compute the Q value of the next state-action...