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

Monte Carlo prediction

In this section, we will learn how to use the Monte Carlo method to perform the prediction task. We have learned that in the prediction task, we will be given a policy and we predict the value function or Q function using the given policy to evaluate it. First, we will learn how to predict the value function using the given policy with the Monte Carlo method. Later, we will look into predicting the Q function using the given policy. Alright, let's get started with the section.

Why do we need the Monte Carlo method for predicting the value function of the given policy? Why can't we predict the value function using the dynamic programming methods we learned about in the previous chapter? We learned that in order to compute the value function using the dynamic programming method, we need to know the model dynamics (transition probability), and when we don't know the model dynamics, we use the model-free methods.

The Monte Carlo method...