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 the chapter by understanding what Stable Baselines is and how to install it. Then, we learned to create our first agent with Stable Baselines using a DQN. We also learned how to save and load an agent. Next, we learned how to create multiple independent environments using vectorization. We also learned about two types of vectorized environment called SubprocVecEnv and DummyVecEnv.

We learned that in SubprocVecEnv, we run each environment in a different process, whereas in DummyVecEnv, we run each environment in the same process.

Later, we learned how to implement a DQN and its variants to play Atari games using Stable Baselines. Next, we learned how to implement A2C and also how to create a custom policy network. Moving on, we learned how to implement DDPG and also how to view the computational graph in TensorBoard.

Going further, we learned how to set up the MuJoCo environment and how to train an agent to walk using TRPO. We also learned how to record...