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

Training an agent to walk using TRPO

In this section, let's learn how to train the agent to walk using Trust Region Policy Optimization (TRPO). Let's use the MuJoCo environment for training the agent. MuJoCo stands for Multi-Joint dynamics with Contact and is one of the most popular simulators used for training agents to perform continuous control tasks.

Note that MuJoCo is a proprietary physics engine, so we need to acquire a license to use it. Also, MuJoCo offers a free 30-day trial period. Installing MuJoCo requires a specific set of steps. So, in the next section, we will see how to install the MuJoCo environment.

Installing the MuJoCo environment

First, in your home directory, create a new hidden folder called .mujoco. Next, go to the MuJoCo website (https://www.roboti.us/) and download MuJoCo according to your operating system. As shown in Figure 16.6, MuJoCo provides support for Windows, Linux, and macOS:

Figure 16.6: Different MuJoCo versions...