Book Image

Hands-On Q-Learning with Python

By : Nazia Habib
Book Image

Hands-On Q-Learning with Python

By: Nazia Habib

Overview of this book

Q-learning is a machine learning algorithm used to solve optimization problems in artificial intelligence (AI). It is one of the most popular fields of study among AI researchers. This book starts off by introducing you to reinforcement learning and Q-learning, in addition to helping you become familiar with OpenAI Gym as well as libraries such as Keras and TensorFlow. A few chapters into the book, you will gain insights into model-free Q-learning and use deep Q-networks and double deep Q-networks to solve complex problems. This book will guide you in exploring use cases such as self-driving vehicles and OpenAI Gym’s CartPole problem. You will also learn how to tune and optimize Q-networks and their hyperparameters. As you progress, you will understand the reinforcement learning approach to solving real-world problems. You will also explore how to use Q-learning and related algorithms in scientific research. Toward the end, you’ll gain insight into what’s in store for reinforcement learning. By the end of this book, you will be equipped with the skills you need to solve reinforcement learning problems using Q-learning algorithms with OpenAI Gym, Keras, and TensorFlow.
Table of Contents (14 chapters)
Free Chapter
1
Section 1: Q-Learning: A Roadmap
6
Section 2: Building and Optimizing Q-Learning Agents
9
Section 3: Advanced Q-Learning Challenges with Keras, TensorFlow, and OpenAI Gym

Contextual bandits and probability distributions

As we saw in the multi-armed previous chapter, the Multi-Armed Bandit Problem (MABP) can be thought of as lite RL. In the simplest type of problem, we have only actions, rewards, and a probability distribution of reward payouts for each action.

Contextual bandits add a state space or context to the bandit problem, giving us additional information about the environment and providing us with an existing probability distribution for each alternative action we might take, so that we don't have to discover the probability distribution from scratch each time.

Probability and intelligence

What does it mean for an event to have a probability distribution? Where does the probability...