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

MAML in Reinforcement Learning

The algorithm for MAML in the reinforcement learning setting is given as follows:

  1. Say we have a model f parameterized by a parameter and we have a distribution over tasks p(T). First, we randomly initialize the model parameter .
  2. Sample a batch of tasks Ti from a distribution of tasks, that is, Ti ~ p(T).
  3. For each task Ti:
    1. Sample k trajectories using and prepare the training dataset:
    2. Train the model on the training dataset and compute the loss
    3. Minimize the loss using gradient descent and get the optimal parameter as
    4. Sample k trajectories using and prepare the test dataset:
  4. Now, we minimize the loss on the test dataset . Parameterize the model f with the optimal parameter calculated in the previous step and compute the loss . Calculate the gradients of the loss and update our randomly initialized parameter using our test (meta-training) dataset:
  5. Repeat...