Book Image

Mastering Reinforcement Learning with Python

By : Enes Bilgin
Book Image

Mastering Reinforcement Learning with Python

By: Enes Bilgin

Overview of this book

Reinforcement learning (RL) is a field of artificial intelligence (AI) used for creating self-learning autonomous agents. Building on a strong theoretical foundation, this book takes a practical approach and uses examples inspired by real-world industry problems to teach you about state-of-the-art RL. Starting with bandit problems, Markov decision processes, and dynamic programming, the book provides an in-depth review of the classical RL techniques, such as Monte Carlo methods and temporal-difference learning. After that, you will learn about deep Q-learning, policy gradient algorithms, actor-critic methods, model-based methods, and multi-agent reinforcement learning. Then, you'll be introduced to some of the key approaches behind the most successful RL implementations, such as domain randomization and curiosity-driven learning. As you advance, you’ll explore many novel algorithms with advanced implementations using modern Python libraries such as TensorFlow and Ray’s RLlib package. You’ll also find out how to implement RL in areas such as robotics, supply chain management, marketing, finance, smart cities, and cybersecurity while assessing the trade-offs between different approaches and avoiding common pitfalls. By the end of this book, you’ll have mastered how to train and deploy your own RL agents for solving RL problems.
Table of Contents (24 chapters)
Section 1: Reinforcement Learning Foundations
Section 2: Deep Reinforcement Learning
Section 3: Advanced Topics in RL
Section 4: Applications of RL

Thompson (Posterior) sampling

The goal in MAB problems is to estimate the parameter(s) of the reward distribution for each arm (that is ad to display in the above example). In addition, measuring our uncertainty about our estimate is a good way to guide the exploration strategy. This problem very much fits into the Bayesian inference framework, which is what Thompson sampling leverages. Bayesian inference starts with a prior probability distribution, an initial idea, for the parameter , and updates this prior as data becomes available. Here, refers to the mean and variance for a normal distribution, and to the probability of observing a "1" for Bernoulli distribution. So, the Bayesian approach treats the parameter as a random variable given the data.

The formula for this is given by:

In this formula, is the prior distribution of , which represents the current hypothesis on its distribution. represents the data, with which we obtain a posterior...