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

Trust region policy optimization

TRPO is one of the most popularly used algorithms in deep reinforcement learning. TRPO is a policy gradient algorithm and it acts as an improvement to the policy gradient with baseline method we learned in Chapter 10, Policy Gradient Method. We learned that policy gradient is an on-policy method, meaning that on every iteration, we improve the same policy with which we are generating trajectories. On every iteration, we update the parameter of our network and try to find the improved policy. The update rule for updating the parameter of our network is given as follows:

Where is the gradient and is known as the step size or learning rate. If the step size is large then there will be a large policy update, and if it is small then there will be a small update in the policy. How can we find an optimal step size? In the policy gradient method, we keep the step size small and so on every iteration there will be a small improvement in the...