Training with reinforcement on Pytorch. Collection of recipes. Over 60 design recipes, development

The Pytorch library enters the advanced position as a tool for reinforcement (OP) due to the effectiveness and ease of its use. This book is organized as a Pytorch reference book, covering a wide range of topics from the very basics (setting up the working environment) to practical tasks (consideration of the OP with specific examples).
You will learn how to use the algorithm of “multi-armed bandits” and the approximation of functions, learn how to win the Atari games using deep Q-networks and how to effectively implement the method of the gradient of the strategy, see how to apply the OP method to the game in blackjack, to others. Wednesdays in the mesh world, to optimize advertising on the Internet and to the game Flappy Bird.
The publication is intended for artificial intelligence specialists who require help in solving the problems of OP. To study the material, acquaintance with the concepts of machine learning, experience with the Pytorch library is not necessary, but desirable