The Comparison of Meta-heuristic and Reinforcement Learning Approach to Implement a Given Qubit Logic

Авторы: Sergeev Mikhail, Bastrakova Marina, Vozhakov Vsevolod, Soloviev Igor, Klenov Nikolay, Kulandin Denis, Linyov Alexey
Сборник: Mathematical Modeling and Supercomputer Technologies
Серия: Communications in Computer and Information Science
Том: 2363
Год издания: 2025
Издательство: Springer Nature
Местоположение издательства: Switzerland
Первая страница: 17
Последняя страница: 30
DOI: 10.1007/978-3-031-80457-1_2
Аннотация: We introduce the detailed comparison of meta-heuristic and reinforcement learning algorithms implementation in the area of quan-tum computations on the example of effective optimization of quantum control scheme to produce quantum logic gates with maximum fidelity to their theoretical counterpart. In particular, we compare the decision mak-ing process of the Genetic Algorithm (GA) as a meta-heuristic algorithm and Proximal Policy Optimization (PPO) as a reinforcement learning algorithm. We provide the comparison via the t-SNE and UMAP dimen-sionality reduction algorithms and analyze solution exploration process for each algorithm based on the reduced representation of generated solu-tions during training. Besides, a detailed review of the investigated prob-lems and the algorithms used in the paper is given.
Добавил в систему: Соловьев Игорь Игоревич

	ИСТИНА	Войти в систему Регистрация
	ИСТИНА ПсковГУ
	Главная Поиск Статистика О проекте Помощь

ИСТИНА