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

Is DP applicable to all environments?

In dynamic programming, that is, in the value and policy iteration methods, we try to find the optimal policy.

Value iteration: In the value iteration method, we compute the optimal value function by taking the maximum over the Q function (Q values) iteratively:

Where . After finding the optimal value function, we extract the optimal policy from it.

Policy iteration: In the policy iteration method, we compute the optimal value function using the policy iteratively:

We will start off with the random policy and compute the value function. Once we have found the optimal value function, then the policy that is used to create the optimal value function will be the optimal policy.

If you look at the preceding two equations, in order to find the optimal policy, we compute the value function and Q function. But to compute the value and the Q function, we need to know the transition probability of the environment, and...