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

Meta reinforcement learning

In order to understand how meta reinforcement learning works, first let's understand meta learning.

Meta learning is one of the most promising and trending research areas in the field of artificial intelligence. It is believed to be a stepping stone for attaining Artificial General Intelligence (AGI). What is meta learning? And why do we need meta learning? To answer these questions, let's revisit how deep learning works.

We know that in deep learning, we train a deep neural network to perform a task. But the problem with deep neural networks is that we need to have a large training dataset to train our network, as it will fail to learn when we have only a few data points.

Let's say we trained a deep learning model to perform task A. Suppose we have a new task B, which is closely related to task A. Although task B is closely related to task A, we can't use the model we trained for task A to perform task B. We need to train...