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 this chapter by understanding what meta learning is. We learned that with meta learning, we train our model on various related tasks with a few data points, such that for a new related task, our model can make use of the learning obtained from the previous tasks.

Next, we learned about a popular meta-learning algorithm called MAML. In MAML, we sample a batch of tasks and for each task Ti in the batch, we minimize the loss using gradient descent and get the optimal parameter . Then, we update our randomly initialized model parameter by calculating the gradients for each of the new tasks Ti with the model parameterized as .

Moving on, we learned about HRL, where we decompose large problems into small subproblems in a hierarchy. We also looked into the different methods used in HRL, such as state-space decomposition, state abstraction, and temporal abstraction. Next, we got an overview of MAXQ value function decomposition, where we decompose the...