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

Summary

We started off the chapter by understanding what the MAB problem is and how it can be solved using several exploration strategies. We first learned about the epsilon-greedy method, where we select a random arm with a probability epsilon and select the best arm with a probability 1-epsilon. Next, we learned about the softmax exploration method, where we select the arm based on the probability distribution, and the probability of each arm is proportional to the average reward.

Following this, we learned about the UCB algorithm, where we select the arm that has the highest upper confidence bound. Then, we explored the Thomspon sampling method, where we learned the distributions of the arms based on the beta distribution.

Moving forward, we learned how MAB can be used as an alternative to AB testing and how can we find the best advertisement banner by framing the problem as a MAB problem. At the end of the chapter, we also had an overview of contextual bandits.

In...