國立高雄大學圖資館 |

登入

回首頁

Reinforcement learning with hybrid quantum approximation in the NISQ context

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Reinforcement learning with hybrid quantum approximation in the NISQ contextby Leonhard Kunczik.
作者:	Kunczik, Leonhard.
出版者:	Wiesbaden :Springer Fachmedien Wiesbaden :2022.
面頁冊數:	xviii, 134 p. :ill., digital ;24 cm.
Contained By:	Springer Nature eBook
標題:	Reinforcement learning.
電子資源:	https://doi.org/10.1007/978-3-658-37616-1
ISBN:	9783658376161$q(electronic bk.)

Reinforcement learning with hybrid quantum approximation in the NISQ context
Kunczik, Leonhard.

Reinforcement learning with hybrid quantum approximation in the NISQ context[electronic resource] /by Leonhard Kunczik. - Wiesbaden :Springer Fachmedien Wiesbaden :2022. - xviii, 134 p. :ill., digital ;24 cm.

Motivation: Complex Attacker-Defender Scenarios - The eternal conﬂict., The Information Game - A special Attacker-Defender Scenario., Reinforcement Learning and Bellman's Principle of Optimality., Quantum Reinforcement Learning - Connecting Reinforcement Learning and Quantum Computing -- Approximation in Quantum Computing -- Advanced Quantum Policy Approximation in Policy Gradient Rein-forcement Learning -- Applying Quantum REINFORCE to the Information Game -- Evaluating quantum REINFORCE on IBM's Quantum Hardware -- Future Steps in Quantum Reinforcement Learning for Complex Scenarios -- Conclusion.

This book explores the combination of Reinforcement Learning and Quantum Computing in the light of complex attacker-defender scenarios. Reinforcement Learning has proven its capabilities in different challenging optimization problems and is now an established method in Operations Research. However, complex attacker-defender scenarios have several characteristics that challenge Reinforcement Learning algorithms, requiring enormous computational power to obtain the optimal solution. The upcoming field of Quantum Computing is a promising path for solving computationally complex problems. Therefore, this work explores a hybrid quantum approach to policy gradient methods in Reinforcement Learning. It proposes a novel quantum REINFORCE algorithm that enhances its classical counterpart by Quantum Variational Circuits. The new algorithm is compared to classical algorithms regarding the convergence speed and memory usage on several attacker-defender scenarios with increasing complexity. In addition, to study its applicability on today's NISQ hardware, the algorithm is evaluated on IBM's quantum computers, which is accompanied by an in-depth analysis of the advantages of Quantum Reinforcement Learning. About the author Leonhard Kunczik obtained his Dr. rer. nat. in 2021 in Quantum Reinforcement Learning from the Universitat der Bundeswehr Munchen as a member of the COMTESSA research group. Now, he continues his research as a project leader at the forefront of Quantum Machine Learning and Optimization in the context of Operations Research and Cyber Security.

ISBN: 9783658376161$q(electronic bk.)

Standard No.: 10.1007/978-3-658-37616-1doiSubjects--Topical Terms:

349131
Reinforcement learning.

LC Class. No.: Q325.6 / .K85 2022

Dewey Class. No.: 006.31

Reinforcement learning with hybrid quantum approximation in the NISQ context
LDR:03194nmm a2200325 a 4500 001 621462
003 DE-He213
005 20220531113640.0
006 m d
007 cr nn 008maaau
008 221121s2022 gw s 0 eng d
020 $a 9783658376161$q(electronic bk.)
020 $a 9783658376154$q(paper)
024 7 $a 10.1007/978-3-658-37616-1 $2 doi
035 $a 978-3-658-37616-1
040 $a GP $c GP
041 0 $a eng
050 4 $a Q325.6 $b .K85 2022
072 7 $a UYQM $2 bicssc
072 7 $a COM004000 $2 bisacsh
072 7 $a UYQM $2 thema
082 0 4 $a 006.31 $2 23
090 $a Q325.6 $b .K96 2022
100 1 $a Kunczik, Leonhard. $3 922676
245 1 0 $a Reinforcement learning with hybrid quantum approximation in the NISQ context $h [electronic resource] / $c by Leonhard Kunczik.
260 $a Wiesbaden : $b Springer Fachmedien Wiesbaden : $b Imprint: Springer Vieweg, $c 2022.
300 $a xviii, 134 p. : $b ill., digital ; $c 24 cm.
505 0 $a Motivation: Complex Attacker-Defender Scenarios - The eternal conﬂict., The Information Game - A special Attacker-Defender Scenario., Reinforcement Learning and Bellman's Principle of Optimality., Quantum Reinforcement Learning - Connecting Reinforcement Learning and Quantum Computing -- Approximation in Quantum Computing -- Advanced Quantum Policy Approximation in Policy Gradient Rein-forcement Learning -- Applying Quantum REINFORCE to the Information Game -- Evaluating quantum REINFORCE on IBM's Quantum Hardware -- Future Steps in Quantum Reinforcement Learning for Complex Scenarios -- Conclusion.
520 $a This book explores the combination of Reinforcement Learning and Quantum Computing in the light of complex attacker-defender scenarios. Reinforcement Learning has proven its capabilities in different challenging optimization problems and is now an established method in Operations Research. However, complex attacker-defender scenarios have several characteristics that challenge Reinforcement Learning algorithms, requiring enormous computational power to obtain the optimal solution. The upcoming field of Quantum Computing is a promising path for solving computationally complex problems. Therefore, this work explores a hybrid quantum approach to policy gradient methods in Reinforcement Learning. It proposes a novel quantum REINFORCE algorithm that enhances its classical counterpart by Quantum Variational Circuits. The new algorithm is compared to classical algorithms regarding the convergence speed and memory usage on several attacker-defender scenarios with increasing complexity. In addition, to study its applicability on today's NISQ hardware, the algorithm is evaluated on IBM's quantum computers, which is accompanied by an in-depth analysis of the advantages of Quantum Reinforcement Learning. About the author Leonhard Kunczik obtained his Dr. rer. nat. in 2021 in Quantum Reinforcement Learning from the Universitat der Bundeswehr Munchen as a member of the COMTESSA research group. Now, he continues his research as a project leader at the forefront of Quantum Machine Learning and Optimization in the context of Operations Research and Cyber Security.
650 0 $a Reinforcement learning. $3 349131
650 0 $a Quantum computing. $3 725269
650 1 4 $a Machine Learning. $3 833608
650 2 4 $a Data and Information Security. $3 913130
650 2 4 $a Security Services. $3 825729
650 2 4 $a Computer Crime. $3 833604
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer Nature eBook
856 4 0 $u https://doi.org/10.1007/978-3-658-37616-1
950 $a Mathematics and Statistics (SpringerNature-11649)