Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Ivan Koryakovskiy"'
Autor:
Egor Shvetsov, Dmitry Osin, Alexey Zaytsev, Ivan Koryakovskiy, Valentin Buchnev, Ilya Trofimov, Evgeny Burnaev
Publikováno v:
IEEE Access, Vol 12, Pp 117008-117025 (2024)
This work aims to develop an automated procedure for discovering new, efficient solutions that can be effectively quantized in mixed-precision mode with minimal degradation. While our primary focus is on Super-Resolution (SR), our proposed procedure
Externí odkaz:
https://doaj.org/article/28f9e361f50948308b3f2684785145c8
Publikováno v:
IFAC-PapersOnLine. 50:6928-6933
Reinforcement learning techniques enable robots to deal with their own dynamics and with unknown environments without using explicit models or preprogrammed behaviors. However, reinforcement learning relies on intrinsically risky exploration, which i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f1bfa55008f00abc1642ac7c64735afd
https://doi.org/10.1016/j.ifacol.2017.08.1218
https://doi.org/10.1016/j.ifacol.2017.08.1218
Autor:
Manuel Kudruss, Katja Mombaur, Ivan Koryakovskiy, Wouter Caarls, Christian Kirches, Heike Vallery, Robert Babuka, Johannes P. Schlder
Publikováno v:
Robotics and Autonomous Systems, 92
Model-free reinforcement learning and nonlinear model predictive control are two different approaches for controlling a dynamic system in an optimal way according to a prescribed cost function. Reinforcement learning acquires a control policy through
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b7c2e993c5f061c933a646bcee6c2fe6
https://doi.org/10.1016/j.robot.2017.02.006
https://doi.org/10.1016/j.robot.2017.02.006
Publikováno v:
IEEE Robotics and Automation Letters, 3(3)
Learning-based approaches are suitable for the control of systems with unknown dynamics. However, learning from scratch involves many trials with exploratory actions until a good control policy is discovered. Real robots usually cannot withstand the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::348c6f8447f9d16436b1a4b9410ba562
http://resolver.tudelft.nl/uuid:4ea9a42f-9d8a-4080-936e-d603feaac5ab
http://resolver.tudelft.nl/uuid:4ea9a42f-9d8a-4080-936e-d603feaac5ab
Publikováno v:
GECCO
In this paper, a new genetic algorithm (GA) for solving the path planning in dynamic environments is proposed. The new genetic algorithm uses local maps, therefore, does not require the knowledge of exact or estimated position of the destination poin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::efa7ffc1204426ecead7f1b581fb0482
https://doi.org/10.1145/1569901.1570203
https://doi.org/10.1145/1569901.1570203