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

Swinging up a pendulum using DDPG

Let's learn how to implement the DDPG for the inverted pendulum swing-up task using Stable Baselines. First, let's import the necessary libraries:

import gym
import numpy as np
from stable_baselines.ddpg.policies import MlpPolicy
from stable_baselines.common.noise import NormalActionNoise, OrnsteinUhlenbeckActionNoise, AdaptiveParamNoiseSpec
from stable_baselines import DDPG

Create the pendulum environment using Gym:

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

Get the number of actions:

n_actions = env.action_space.shape[-1]

We know that in DDPG, instead of selecting the action directly, we add some noise using the Ornstein-Uhlenbeck process to ensure exploration. So, we create the action noise as follows:

action_noise = OrnsteinUhlenbeckActionNoise(mean=np.zeros(n_actions), sigma=float(0.5) * np.ones(n_actions))

Instantiate the agent:

agent = DDPG(MlpPolicy, env, verbose=1, param_noise=None, action_noise...