Book Image

Reinforcement Learning Algorithms with Python

By : Andrea Lonza
Book Image

Reinforcement Learning Algorithms with Python

By: Andrea Lonza

Overview of this book

Reinforcement Learning (RL) is a popular and promising branch of AI that involves making smarter models and agents that can automatically determine ideal behavior based on changing requirements. This book will help you master RL algorithms and understand their implementation as you build self-learning agents. Starting with an introduction to the tools, libraries, and setup needed to work in the RL environment, this book covers the building blocks of RL and delves into value-based methods, such as the application of Q-learning and SARSA algorithms. You'll learn how to use a combination of Q-learning and neural networks to solve complex problems. Furthermore, you'll study the policy gradient methods, TRPO, and PPO, to improve performance and stability, before moving on to the DDPG and TD3 deterministic algorithms. This book also covers how imitation learning techniques work and how Dagger can teach an agent to drive. You'll discover evolutionary strategies and black-box optimization techniques, and see how they can improve RL algorithms. Finally, you'll get to grips with exploration approaches, such as UCB and UCB1, and develop a meta-algorithm called ESBAS. By the end of the book, you'll have worked with key RL algorithms to overcome challenges in real-world applications, and be part of the RL research community.
Table of Contents (19 chapters)
Free Chapter
1
Section 1: Algorithms and Environments
5
Section 2: Model-Free RL Algorithms
11
Section 3: Beyond Model-Free Algorithms and Improvements
17
Assessments

Epochal stochastic bandit algorithm selection

The main use of exploration strategies in reinforcement learning is to help the agent in the exploration of the environment. We saw this use case in DQN with -greedy, and in other algorithms with the injection of additional noise into the policy. However, there are other ways of using exploration strategies. So, to better grasp the exploration concepts that have been presented so far, and to introduce an alternative use case of these algorithms, we will present and develop an algorithm called ESBAS. This algorithm was introduced in the paper, Reinforcement Learning Algorithm Selection.

ESBAS is a meta-algorithm for online algorithm selection (AS) in the context of reinforcement learning. It uses exploration methods in order to choose the best algorithm to employ during a trajectory, so as to maximize the expected reward.

In order to...