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

Monte Carlo control

In the control task, our goal is to find the optimal policy. Unlike the prediction task, here, we will not be given any policy as an input. So, we will begin by initializing a random policy, and then we try to find the optimal policy iteratively. That is, we try to find an optimal policy that gives the maximum return. In this section, we will learn how to perform the control task to find the optimal policy using the Monte Carlo method.

Okay, we learned that in the control task our goal is to find the optimal policy. First, how can we compute a policy? We learned that the policy can be extracted from the Q function. That is, if we have a Q function, then we can extract policy by selecting an action in each state that has the maximum Q value as the following shows:

So, to compute a policy, we need to compute the Q function. But how can we compute the Q function? We can compute the Q function similarly to what we learned in the MC prediction method. That...