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



ACKTR, math concepts 540

block diagonal matrix 540, 541

block matrix 540

Kronecker product 542

Kronecker product, properties 543

vec operator 543

action 2, 39

actions 14

action space 18, 40, 73, 74

activation function 265

about 267

exploring 267

Rectified Linear Unit (ReLU) function 269, 270

sigmoid function 268

softmax function 270, 271

tanh function 269

activation map 300

Actor Critic 431

actor critic algorithm 428, 429

actor critic class

action, selecting 441

defining 436

global network, updating 440

init method, defining 436, 437, 439

network, building 440

worker network, updating 441

actor critic method

K-FAC, applying 546, 547, 548

overview 424, 425

working 425, 426, 427

Actor Critic using Kronecker-Factored Trust Region (ACKTR) 538, 539

actor network 598, 599

Advantage 431

Advantage Actor Critic (A2C)

about 429, 430