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)
18
Other Books You May Enjoy
19
Index

Summary

We started the chapter by understanding what the Monte Carlo method is. We learned that in the Monte Carlo method, we approximate the expectation of a random variable by sampling, and when the sample size is greater, the approximation will be better. Then we learned about the prediction and control tasks. In the prediction task, we evaluate the given policy by predicting the value function or Q function, which helps us to understand the expected return an agent would get if it uses the given policy. In the control task, our goal is to find the optimal policy, and we will not be given any policy as input, so we start by initializing a random policy and we try to find the optimal policy iteratively.

Moving forward, we learned how to use the Monte Carlo method to perform the prediction task. We learned that the value of a state and the value of a state-action pair can be computed by just taking the average return of the state and an average return of state-action pair across...