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

Proximal policy optimization

In the previous section, we learned how TRPO works. We learned that TRPO keeps the policy updates in the trust region by imposing a constraint that the KL divergence between the old and new policy should be less than or equal to . The problem with the TRPO method is that it is difficult to implement and is computationally expensive. So, now we will learn one of the most popular and state-of-the-art policy gradient algorithms called Proximal Policy Optimization (PPO).

PPO improves upon the TRPO algorithm and is simple to implement. Similar to TRPO, PPO ensures that the policy updates are in the trust region. But unlike TRPO, PPO does not use any constraints in the objective function. Going forward, we will learn how exactly PPO works and how PPO ensures that the policy updates are in the trust region.

There are two different types of PPO algorithm:

  • PPO-clipped – In the PPO-clipped method, in order to ensure that the policy updates...