Book Image

Deep Reinforcement Learning with Python - Second Edition

By : Sudharsan Ravichandiran
Book Image

Deep Reinforcement Learning with Python - Second Edition

By: Sudharsan Ravichandiran

Overview of this book

With significant enhancements in the quality and quantity of algorithms in recent years, this second edition of Hands-On Reinforcement Learning with Python has been revamped into an example-rich guide to learning state-of-the-art reinforcement learning (RL) and deep RL algorithms with TensorFlow 2 and the OpenAI Gym toolkit. In addition to exploring RL basics and foundational concepts such as Bellman equation, Markov decision processes, and dynamic programming algorithms, this second edition dives deep into the full spectrum of value-based, policy-based, and actor-critic RL methods. It explores state-of-the-art algorithms such as DQN, TRPO, PPO and ACKTR, DDPG, TD3, and SAC in depth, demystifying the underlying math and demonstrating implementations through simple code examples. The book has several new chapters dedicated to new RL techniques, including distributional RL, imitation learning, inverse RL, and meta RL. You will learn to leverage stable baselines, an improvement of OpenAI’s baseline library, to effortlessly implement popular RL algorithms. The book concludes with an overview of promising approaches such as meta-learning and imagination augmented agents in research. By the end, you will become skilled in effectively employing RL and deep RL in your real-world projects.
Table of Contents (22 chapters)
18
Other Books You May Enjoy
19
Index

Contextual bandits

We just learned how to use bandits to find the best advertisement banner for the users. But the banner preference varies from user to user. That is, user A likes banner 1, but user B might like banner 3, and so on. Each user has their own preferences. So, we have to personalize advertisement banners according to each user. How can we do that? This is where we use contextual bandits.

In the MAB problem, we just perform the action and receive a reward. But with contextual bandits, we take actions based on the state of the environment and the state holds the context.

For instance, in the advertisement banner example, the state specifies the user behavior and we will take action (show the banner) according to the state (user behavior) that will result in the maximum reward (ad clicks).

Contextual bandits are widely used for personalizing content according to the user's behavior. They are also used to solve the cold-start problems faced by recommendation...