Zobrazeno 1 - 10
of 62
pro vyhledávání: '"Sachiyo Arai"'
Autor:
Daiko Kishikawa, Sachiyo Arai
Publikováno v:
IEEE Access, Vol 12, Pp 128519-128524 (2024)
Inverse reinforcement learning (IRL) is a technique that estimates the intention of an expert who acts optimally on a specific intention, as a reward from demonstration (i.e., recorded data of the expert’s behavior). Traditional IRL algorithms are
Externí odkaz:
https://doaj.org/article/b1e08c5e64834489965c8b0217efa385
Autor:
Akinori Tamura, Sachiyo Arai
Publikováno v:
IEEE Access, Vol 12, Pp 97280-97297 (2024)
Reinforcement learning, which is attracting attention as a method for optimizing sequential decision-making, primarily focuses on scenarios with a single objective. In contrast, real-world decision-making involves multiple objectives, often with trad
Externí odkaz:
https://doaj.org/article/65281e927a38427b8558707de5de0f6a
Autor:
Daiko Kishikawa, Sachiyo Arai
Publikováno v:
SICE Journal of Control, Measurement, and System Integration, Vol 16, Iss 1, Pp 140-151 (2023)
Multi-objective inverse reinforcement learning (MOIRL) extends inverse reinforcement learning (IRL) to multi-objective problems by estimating weights and multi-objective rewards to help retrain and analyse preference-conditioned behaviour. Unlike pre
Externí odkaz:
https://doaj.org/article/7f6b5445c37c4c9cae4b0435a625f6fc
Autor:
Takumi Saiki, Sachiyo Arai
Publikováno v:
IEEE Access, Vol 11, Pp 75875-75883 (2023)
Deep reinforcement learning has been extensively studied for traffic signal control owing to its ability to process large amounts of information and achieving superior performance control. However, this method acquires flow-specific policies during l
Externí odkaz:
https://doaj.org/article/c7901c511f2a4e23a54cf74f87460b63
Autor:
Naoya Takayama, Sachiyo Arai
Publikováno v:
IEEE Access, Vol 11, Pp 58532-58538 (2023)
Several real-world problems are modeled as multi-objective sequential decision-making problems with multiple competing objectives, and multi-objective reinforcement learning (MORL) has garnered attention as a solution to this problem. One of the chal
Externí odkaz:
https://doaj.org/article/a57c072d417c4ae59bfd2506960c5619
Publikováno v:
IEEE Access, Vol 11, Pp 43128-43139 (2023)
Sequential decision-making problems with multiple objectives are known as multi-objective reinforcement learning. In these scenarios, decision-makers require a complete Pareto front that consists of Pareto optimal solutions. Such a front enables deci
Externí odkaz:
https://doaj.org/article/3c2dcab280274e4f994b6f59af3e4f83
Publikováno v:
Journal of Marine Science and Engineering, Vol 11, Iss 10, p 2014 (2023)
This study introduces a hybrid control structure called Improved Interfered Fluid Dynamic System Nonlinear Model Predictive Control (IIFDS-NMPC) for the path planning and trajectory tracking of autonomous underwater vehicles (AUVs). The system consis
Externí odkaz:
https://doaj.org/article/9b5d19e1e828498aab333808bdc040fe
Publikováno v:
Journal of Marine Science and Engineering, Vol 11, Iss 3, p 588 (2023)
The Deep Reinforcement Learning (DRL) algorithm is an optimal control method with generalization capacity for complex nonlinear coupled systems. However, the DRL agent maintains control command saturation and response overshoot to achieve the fastest
Externí odkaz:
https://doaj.org/article/07557130f39e4944938c315f6bb847f1
Publikováno v:
Journal of Process Control. 122:41-48
Autor:
Naoya Takayama, Sachiyo Arai
Publikováno v:
Artificial Life and Robotics. 27:594-602