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

Deep Q learning from demonstrations

We learned that in imitation learning, we try to learn from expert demonstrations. Can we make use of expert demonstrations in DQN and perform better? Yes! In this section, we will learn how to make use of expert demonstrations in DQN using an algorithm called DQfD.

In the previous chapters, we have learned about several types of DQN. We started off with vanilla DQN, and then we explored various improvements to the DQN, such as double DQN, dueling DQN, prioritized experience replay, and more. In all these methods, the agent tries to learn from scratch by interacting with the environment. The agent interacts with the environment and stores their interaction experience in a buffer called a replay buffer and learns based on their experience.

In order for the agent to perform better, it has to gather a lot of experience from the environment, add it to the replay buffer, and train itself. However, this method costs us a lot of training...