Deep Reinforcement Learning with Python - Second Edition
Langue : anglais
Edité par Packt Publishing, 2020
- Livre broché
- Neuf
Vendeur : preigu, Osnabrück, Allemagnepreigu
Vendeur AbeBooks depuis 5 août 2024
Etat: Neuf
EUR 66,05
Quantité disponible : 5 disponibles
Ajouter au panierA propos de cet article
Deep Reinforcement Learning with Python - Second Edition | Sudharsan Ravichandiran | Taschenbuch | Kartoniert / Broschiert | Englisch | 2020 | Packt Publishing | EAN 9781839210686 | Verantwortliche Person für die EU: Libri GmbH, Europaallee 1, 36244 Bad Hersfeld, gpsr[at]libri[dot]de | Anbieter: preigu Print on Demand.
N° de réf. du vendeur 119404972
- Titre
- Deep Reinforcement Learning with Python - Second Edition
- Auteur
- Sudharsan Ravichandiran
- Éditeur
- Packt Publishing
- Année de publication
- 2020
- État de l'article
- Neu
- Reliure
- Taschenbuch
- Langue
- anglais
- ISBN à 10 chiffres
- 1839210680
- ISBN à 13 chiffres
- 9781839210686
- Édition
- 2ème Édition
- Poids de l'article
- 1 392 grammes
- Dimensions
- 235 x 191 x 41 mm
- Catalogues du vendeur
- Bücher
An example-rich guide for beginners to start their reinforcement and deep reinforcement learning journey with state-of-the-art distinct algorithms
Key Features
- Covers a vast spectrum of basic-to-advanced RL algorithms with mathematical explanations of each algorithm
- Learn how to implement algorithms with code by following examples with line-by-line explanations
- Explore the latest RL methodologies such as DDPG, PPO, and the use of expert demonstrations
Book Description
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.
What you will learn
- Understand core RL concepts including the methodologies, math, and code
- Train an agent to solve Blackjack, FrozenLake, and many other problems using OpenAI Gym
- Train an agent to play Ms Pac-Man using a Deep Q Network
- Learn policy-based, value-based, and actor-critic methods
- Master the math behind DDPG, TD3, TRPO, PPO, and many others
- Explore new avenues such as the distributional RL, meta RL, and inverse RL
- Use Stable Baselines to train an agent to walk and play Atari games
Who this book is for
If you're a machine learning developer with little or no experience with neural networks interested in artificial intelligence and want to learn about reinforcement learning from scratch, this book is for you.
Basic familiarity with linear algebra, calculus, and the Python programming language is required. Some experience with TensorFlow would be a plus.
Table of Contents
- Fundamentals of Reinforcement Learning
- A Guide to the Gym Toolkit
- The Bellman Equation and Dynamic Programming
- Monte Carlo Methods
- Understanding Temporal Difference Learning
- Case Study - The MAB Problem
- Deep Learning Foundations
- A Primer on TensorFlow
- Deep Q Network and Its Variants
- Policy Gradient Method
- Actor-Critic Methods - A2C and A3C
- Learning DDPG, TD3, and SAC
- TRPO, PPO, and ACKTR Methods
- Distributional Reinforcement Learning
- Imitation Learning and Inverse RL
- Deep Reinforcement Learning with Stable Baselines
- Reinforcement Learning Frontiers
- Appendix 1 - Reinforcement Learning Algorithms
- Appendix 2 - Assessments
« Synopsis » peut appartenir à une autre édition de cet ouvrage.
À propos de l’auteur
Sudharsan Ravichandiran is a data scientist, researcher, best selling author, and YouTuber (search for "Sudharsan reinforcement learning"). He completed his Bachelor's in Information Technology at Anna University. His area of research focuses on practical implementations of deep learning and reinforcement learning, including Natural Language Processing and computer vision. He is an open-source contributor and loves answering questions on Stack Overflow. He also authored a best-seller, Hands-On Reinforcement Learning with Python, published by Packt Publishing.
« A propos de ce titre » peut appartenir à une autre édition de cet ouvrage.
preigu
Osnabrück, Allemagne
Vendeur AbeBooks depuis 5 août 2024
Frais d'expédition de Allemagne vers Etats-Unis
| Article | 60 à 60 jours ouvrés | 60 à 60 jours ouvrés |
|---|---|---|
| Premier article | EUR 70,00 | EUR 70,00 |
Modes de paiement
- Paypal
Description de la boutique
preigu betreibt einen Onlineversandhandel mit über 1 Mio. Produkten in verschiedenen Sortimenten. Das Kernsortiment besteht aus Büchern, Medien und Spielwaren. Ein gelungenes Einkaufserlebnis ist das Ziel einer jeden Bestellung bei preigu, denn der Kunde und seine Zufriedenheit stehen an erster Stelle. preigu setzt daher auf einen kompetenten Kundenservice, funktionierende Prozesse und schnelle Reaktion.
Spécialité
Bücher, SpielwarenProfil professionnel du vendeur
preigu GmbH & Co. KG
Lengericher Landstraße 19
Osnabrück, Allemagne 49078
Conditions de vente
About Us
Legal website operator identification:
preigu GmbH & Co. KG
Lengericher Landstr. 19
49078 Osnabrück
Germany
Telephone: +49 (0) 541 / 580 72 84
Email: mail@preigu.de
VAT No: DE 455 380 498
AG Osnabrück - HRA 209647
PhG: preigu Verwaltung GmbH
AG Osnabrück - HRB 221793
CEO: Ansas Meyer
We are neither willing nor obliged to participate in dispute resolution proceedings before consumer arbitration boards.
We are a member of the initiative "FairCommerce" since 30.11.2016.
For more information, see: https://www.haendlerbund.de/de/haendlerbund/interessenvertretung/faircommerce
Droit de rétractation
Instructions for revocation
Right of withdrawal for the sale of goods
Revocation right for consumers
(A ‘consumer' is any natural person who concludes a legal transaction which, to an overwhelming extent, cannot be attributed to either his commercial or independent professional activities.)
Instructions for revocation
Revocation right
You have the right to revoke this contract within 14 days without specifying any reasons.
The revocation period is 14 days with effect from the day,
-
on which you or a third party nominated by you, which is not the carrier, had taken possession of the products, provided you had ordered one or more products within the scope of a standard order and this/these product/products is/are delivered uniformly;
-
on which you or a third party nominated by you, which is not the carrier, had taken possession of the last product, provided you had ordered several products within the scope of a standard order and these products are delivered separately;
-
on which you or a third party nominated by you, which is not the carrier, had taken possession of the last part delivery or the last unit, provided you had ordered a product, which is delivered in several part deliveries or units;
To exercise your right of withdrawal, you must inform us (preigu GmbH & Co. KG, Lengericher Landstr. 19, 49078 Osnabrück, Telephone number: +49 (0) 541 / 580 72 84, E-Mail address: mail@preigu.de) by means of a clear declaration (e.g. a letter sent by post, or an e-mail) of your decision to withdraw from this contract. You can use the attached model withdrawal form for this purpose, which is, however, not mandatory.
You can also exercise your right of withdrawal online by clicking on a button labelled accordingly (such as ‘Withdraw from contract' or similar) on the AbeBooks/ZVAB website. If you use this online function, you will immediately receive a confirmation of receipt on a durable medium (e.g. via email) containing information on the content of the withdrawal notice, as well as the date and time of its receipt.
In order to safeguard the revocation period, it is sufficient that you send the notification about the exercise of the revocation right before the expiry of the revocation period.
Consequences of the revocation
If you revoke this contract, we shall repay all the payments, which we received from you, including the delivery costs (with the exception of additional costs, which arise from that fact that you selected a form of delivery other than the most reasonable standard delivery offered by us), immediately and at the latest within 14 days from the day on which we received the notification about the revocation of this contract from you. We use the same means of payment, which you had originally used during the original transaction, for this repayment unless expressly agreed otherwise with you; you will not be charged any fees owing to this repayment.
We can refuse the repayment until the products are returned to us or until you have furnished evidence that you have sent the products back to us, depending on whichever is earlier.
You must return or transfer the products to us immediately and, in any case, at the latest within 14 days with effect from the day on which you inform us of the revocation of this contract. The deadline is maintained if you send the products before the expiry of the 14 day deadline.
You bear the direct costs for returning the products.
You must pay for any depreciation of the products only if this depreciation can be attributed to any handling with you that was not necessary for checking the condition, features and functionality of the products.
Criteria for exclusion or expiry
The revocation right is not available for contracts
-
for delivery of products, which are not prefabricated and for whose manufacturing an individual selection or stipulation by the consumer is important or which are clearly tailored to the personal requirements of the consumer;
-
for delivery of products, which can spoil quickly or whose use-by date would be exceeded quickly;
-
for delivery of alcoholic drinks, whose price was agreed at the time of concluding the contract, which however can be delivered 30 days after the conclusion of the contract at the earliest and whose current value depends on the fluctuations in the market, on which the entrepreneur has no influence;
-
for delivery of newspapers, periodicals or magazines with the exception of subscription contracts. The revocation right expires prematurely in case of contracts
-
for delivery of sealed products, which are not suitable for return for reasons of health protection or hygiene if their seal has been removed after the delivery;
-
for delivery of products if they have been mixed inseparably with other goods after the delivery, owing to their condition;
-
for delivery of sound or video recording or computer software in a sealed package if the seal has been removed after the delivery.
Specimen - revocation form
(If you wish to revoke the contract, please fill up this form and send it back to us.)
-
To preigu GmbH & Co. KG, Lengericher Landstr. 19, 49078 Osnabrück, Email address: mail@preigu.de :
-
I/we () herewith revoke the contract concluded by me/ us () regarding the purchase of the following products ()/
the provision of the following service () -
Ordered on ()/ received on ()
-
Name of the consumer(s)
-
Address of the consumer(s)
-
Signature of the consumer(s) (only in case of a notification on paper)
-
Date
(*) Cross out the incorrect option.