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

A Guide to the Gym Toolkit

OpenAI is an artificial intelligence (AI) research organization that aims to build artificial general intelligence (AGI). OpenAI provides a famous toolkit called Gym for training a reinforcement learning agent.

Let's suppose we need to train our agent to drive a car. We need an environment to train the agent. Can we train our agent in the real-world environment to drive a car? No, because we have learned that reinforcement learning (RL) is a trial-and-error learning process, so while we train our agent, it will make a lot of mistakes during learning. For example, let's suppose our agent hits another vehicle, and it receives a negative reward. It will then learn that hitting other vehicles is not a good action and will try not to perform this action again. But we cannot train the RL agent in the real-world environment by hitting other vehicles, right? That is why we use simulators and train the RL agent in the simulated environments.

There are many toolkits that provide a simulated environment for training an RL agent. One such popular toolkit is Gym. Gym provides a variety of environments for training an RL agent ranging from classic control tasks to Atari game environments. We can train our RL agent to learn in these simulated environments using various RL algorithms. In this chapter, first, we will install Gym and then we will explore various Gym environments. We will also get hands-on with the concepts we have learned in the previous chapter by experimenting with the Gym environment.

Throughout the book, we will use the Gym toolkit for building and evaluating reinforcement learning algorithms, so in this chapter, we will make ourselves familiar with the Gym toolkit.

In this chapter, we will learn about the following topics:

  • Setting up our machine
  • Installing Anaconda and Gym
  • Understanding the Gym environment
  • Generating an episode in the Gym environment
  • Exploring more Gym environments
  • Cart-Pole balancing with the random agent
  • An agent playing the Tennis game