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

Inverse reinforcement learning

Inverse Reinforcement Learning (IRL) is one of the most exciting fields of reinforcement learning. In reinforcement learning, our goal is to learn the optimal policy. That is, our goal is to find the optimal policy that gives the maximum return (sum of rewards of the trajectory). In order to find the optimal policy, first, we should know the reward function. A reward function tells us what reward we obtain by performing an action a in the state s. Once we have the reward function, we can train our agent to learn the optimal policy that gives the maximum reward. But the problem is that designing the reward function is not that easy for complex tasks.

Consider designing the reward function for tasks such as an agent learning to walk, self-driving cars, and so on. In these cases, designing the reward function is not that handy and involves assigning rewards to a variety of agent behaviors. For instance, consider designing the reward function for an...