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 the Bellman equation of the value and Q functions. We learned that, according to the Bellman equation, the value of a state is the sum of the immediate reward, and the discounted value of the next state and the value of a state-action pair is the sum of the immediate reward and the discounted value of the next state-action pair. Then we learned about the optimal Bellman value function and the Q function, which gives the maximum value.

Moving forward, we learned about the relation between the value and Q functions. We learned that the value function can be extracted from the Q function as and then we learned that the Q function can be extracted from the value function as .

Later we learned about two interesting methods called value iteration and policy iteration, which use dynamic programming to find the optimal policy.

In the value iteration method, first, we compute the optimal value function by...