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

Gradient-based meta-reinforcement learning

Gradient-based meta-RL methods propose improving the policy by continuing the training at test time so that the policy adapts to the environment it is applied in. The key is that policy parameters right before the adaptation, , are set in such a way that the adaptation takes place in just a few shots.


Gradient-based meta-RL is based on the idea that some initializations of policy parameters enable learning from very little data during adaptation. The meta-training procedure aims to find such an initialization.

A specific approach in this branch is called model-agnostic meta-learning (MAML), which is a general meta-learning method that can also be applied in RL. MAML trains the agent for a variety of tasks to figure out a good that facilitates adaptation and learning from few shots.

Let's see how you can use RLlib for this.

RLlib implementation

MAML is one of the agents implemented in RLlib and can be easily used...