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)
1
Section 1: Reinforcement Learning Foundations
7
Section 2: Deep Reinforcement Learning
12
Section 3: Advanced Topics in RL
17
Section 4: Applications of RL

Developing strategies to solve the Kuka environment

The object grasping problem in the environment is a hard-exploration problem, meaning that it is unlikely to stumble upon the sparse reward that the agent receives at the end upon grasping the object. Reducing the vertical speed as we will do will make is a bit easier. Still, let's refresh our minds about what strategies we have covered to address these kinds of problems:

  • Reward shaping is one of the most common machine teaching strategies that we discussed earlier. In some problems, incentivizing the agent towards the goal is very straightforward. In many problems, though, it can be quite painful. So, unless there is an obvious way of doing so, crafting the reward function may just take too much time (and expertise about the problem). Also notice that the original reward function has a component to penalize the distance between the gripper and the object, so the reward is already shaped to some extent. We will not go...