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


We started off the chapter by understanding what TRPO is and how it acts as an improvement to the policy gradient algorithm. We learned that when the new policy and old policy vary greatly then it causes model collapse.

So in TRPO, we make a policy update while imposing the constraint that the parameters of the old and new policies should stay within the trust region. We also learned that TRPO guarantees monotonic policy improvement; that is, it guarantees that there will always be a policy improvement on every iteration.

Later, we learned about the PPO algorithm, which acts as an improvement to the TRPO algorithm. We learned about two types of PPO algorithm: PPO-clipped and PPO-penalty. In the PPO-clipped method, in order to ensure that the policy updates are in the trust region, PPO adds a new function called the clipping function that ensures the new and old policies are not far away from each other. In the PPO-penalty method, we modify our objective function...