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

Deep deterministic policy gradient

DDPG is an off-policy, model-free algorithm, designed for environments where the action space is continuous. In the previous chapter, we learned how the actor-critic method works. DDPG is an actor-critic method where the actor estimates the policy using the policy gradient, and the critic evaluates the policy produced by the actor using the Q function.

DDPG uses the policy network as an actor and deep Q network as a critic. One important difference between the DPPG and actor-critic algorithms we learned in the previous chapter is that DDPG tries to learn a deterministic policy instead of a stochastic policy.

First, we will get an intuitive understanding of how DDPG works and then we will look into the algorithm in detail.

An overview of DDPG

DDPG is an actor-critic method that takes advantage of both the policy-based method and the value-based method. It uses a deterministic policy instead of a stochastic policy .