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

Implementing GAIL

In this section, let's explore how to implement Generative Adversarial Imitation Learning (GAIL) with Stable Baselines. In Chapter 15, Imitation Learning and Inverse RL, we learned that we use the generator to generate the state-action pair in a way that the discriminator is not able to distinguish whether the state-action pair is generated using the expert policy or the agent policy. We train the generator to generate a policy similar to an expert policy using TRPO, while the discriminator is a classifier and it is optimized using Adam.

To implement GAIL, we need expert trajectories so that our generator learns to mimic the expert trajectory. Okay, so how can we obtain the expert trajectory? First, we use the TD3 algorithm to generate expert trajectories and then create an expert dataset. Then, using this expert dataset, we train our GAIL agent. Note that instead of using TD3, we can also use any other algorithm for generating expert trajectories.