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 the chapter by understanding what imitation learning is and how supervised imitation learning works. Next, we learned about the DAgger algorithm, where we aggregate the dataset obtained over a series of iterations and learn the optimal policy.

After looking at DAgger, we learned about DQfD, where we prefill the replay buffer with expert demonstrations and pre-train the agent with expert demonstrations before the training phase.

Moving on, we learned about IRL. We understood that in reinforcement learning, we try to find the optimal policy given the reward function, but in IRL, we try to learn the reward function given the expert demonstrations. When we have derived the reward function from the expert demonstrations using IRL, we can use the reward function to train our agent to learn the optimal policy using any reinforcement learning algorithm. We then explored how to learn the reward function using the maximum entropy IRL algorithm.

At the end...