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

Chapter 4 – Monte Carlo Methods

  1. In the Monte Carlo method, we approximate the value of a state by taking the average return of a state across N episodes instead of taking the expected return.
  2. To compute the value function using the dynamic programming method, we need to know the model dynamics, and when we don't know the model dynamics, we use model-free methods. The Monte Carlo method is a model-free method meaning that it doesn't require the model dynamics (transition probability) to compute the value function.
  3. In a 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 used the given policy. However, in a control task, our goal is to find the optimal policy and are not given any policy as input, so we start by initializing a random policy and try to find the optimal policy iteratively.
  4. In the MC prediction method, the value...