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

Chapter 16 – Deep Reinforcement Learning with Stable Baselines

  1. Stable Baselines is an improved implementation of OpenAI Baselines. Stable Baselines is a high-level library that is easier to use than OpenAI Baselines, and it also includes state-of-the-art deep RL algorithms along with offering several useful features.
  2. We can save the agent as and load the trained agent as agent.load().
  3. We generally train our agent in a single environment per step but with Stable Baselines, we can train our agent in multiple environments per step. This helps our agent to learn quickly. Now, our states, actions, reward, and done will be in the form of a vector since we are training our agent in multiple environments. So, we call this a vectorized environment.
  4. In SubprocVecEnv, we run each environment in a different process, whereas in DummyVecEnv, we run each environment in the same process.
  5. With Stable Baselines, it is easier to view the computational...