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

Vectorized environments

One of the very interesting and useful features of Stable Baselines is that we can train our agent in multiple independent environments either in separate processes (using SubprocVecEnv) or in the same process (using DummyVecEnv).

For example, say we are training our agent in a cart pole balancing environment – instead of training our agent only in a single cart pole balancing environment, we can train our agent in the multiple cart pole balancing environments.

We generally train our agent in a single environment per step but now we can train our agent in multiple environments per step. This helps our agent to learn more quickly. Now, our state, action, 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.

There are two types of vectorized environment offered by Stable Baselines:

  • SubprocVecEnv
  • DummyVecEnv