Don't hope to get rid of books (Umberto Eco)
+371 27000041, +371 27000045
(on working days 9:00-17:00 latvian)
+371 27000041
+371 27000045

(on working days 10:00-17:00)

Reinforcement Learning Algorithms in Python

29.99 €
Out of stock
Reinforcement Learning Algorithms in Python
29.99 €
This book will help the reader to master reinforcement learning (RL) algorithms and learn how to implement them when creating self-learning agents.
The first part discusses the various elements of OO, its scope, and the tools needed to work in an OO environment. The second and third parts deal directly with algorithms. Among other things, the author shows how to combine Q-learning with neural networks to solve complex problems, describes strategy gradient, TRPO and PPO methods to improve performance and robustness, as well as deterministic DDPG and TD3 algorithms. The reader will learn how imitation learning techniques work, and will be introduced to upper confidence bound-based exploration algorithms (UCB and UCB1) and the ESBAS meta-algorithm. The publication is intended for those who are interested in artificial intelligence research, apply deep learning in their work, or want to master reinforcement learning from scratch. A working knowledge of Python at a working level is a prerequisite.
See also:

You might be interested:

Разработка требований  к программному обеспечению
Information technology
Development of software requirements
Vigers Carl, Beatty Joy
29.99 €
In basket
Совершенный код. Практическое руководство по разработке программного обеспечения
Information technology
Code Complete: A Practical Guide to Software Development
McConnell Steve
49.99 €
In basket
Алгоритмы. Руководство по разработке
Information technology
Algorithms: Development Guide
Skiena Stephen
39.99 €
In basket