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)
18
Other Books You May Enjoy
19
Index

The dueling DQN

Before going ahead, let's learn about one of the most important functions in reinforcement learning, called the advantage function. The advantage function is defined as the difference between the Q function and the value function, and it is expressed as:

Okay, but what's the use of an advantage function? What does it signify? First, let's recall the Q function and the value function:

  • Q function: The Q function gives the expected return an agent would obtain starting from state s, performing action a, and following the policy .
  • Value function: The value function gives the expected return an agent would obtain starting from state s and following the policy .

Now if we think intuitively, what's the difference between the Q function and the value function? The Q function gives us the value of a state-action pair, while the value function gives the value of a state irrespective of the action. Now, the difference...