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

Creating our first agent with Stable Baselines

Now, let's build our first deep RL algorithm using Stable Baselines. Let's create a simple agent using a Deep Q Network (DQN) for the mountain car climbing task. We know that in the mountain car climbing task, a car is placed between two mountains and the goal of the agent is to drive up the mountain on the right.

First, let's import gym and DQN from stable_baselines:

import gym
from stable_baselines import DQN

Create a mountain car environment:

env = gym.make('MountainCar-v0')

Now, let's instantiate our agent. As we can observe in the following code, we are passing MlpPolicy, which implies that our network is a multilayer perceptron:

agent = DQN('MlpPolicy', env, learning_rate=1e-3)

Now, let's train the agent by specifying the number of time steps we want to train:


That's it. Building a DQN agent and training...