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)
Other Books You May Enjoy

Quantile Regression DQN

In this section, we will look into another interesting distributional RL algorithm called QR-DQN. It is a distributional DQN algorithm similar to the categorical DQN; however, it has several features that make it more advantageous than a categorical DQN.

Math essentials

Before going ahead, let's recap two important concepts that we use in QR-DQN:

  • Quantile
  • Inverse cumulative distribution function (Inverse CDF)


When we divide our distribution into equal areas of probability, they are called quantiles. For instance, as Figure 14.18 shows, we have divided our distribution into two equal areas of probabilities and we have two quantiles with 50% probability each:

Figure 14.18: 2-quantile plot

Inverse CDF (quantile function)

To understand an inverse cumulative distribution function (inverse CDF), first, let's learn what a cumulative distribution function (CDF) is.

Consider a random variable...