Zobrazeno 1 - 10
of 222
pro vyhledávání: '"Safe learning"'
Autor:
Lunet Yifru, Ali Baheri
Publikováno v:
IEEE Open Journal of Control Systems, Vol 3, Pp 266-281 (2024)
Reinforcement learning (RL) has revolutionized decision-making across a wide range of domains over the past few decades. Yet, deploying RL policies in real-world scenarios presents the crucial challenge of ensuring safety. Traditional safe RL approac
Externí odkaz:
https://doaj.org/article/825cbb00adc845448830631f719dba79
Publikováno v:
Emerging Science Journal, Vol 7, Iss 0, Pp 172-188 (2023)
The study aimed to assess the relationship between a safe learning environment in Emirati schools and the development of student's creative thinking. Using a descriptive method with stratified random sampling, the researchers selected a sample of 500
Externí odkaz:
https://doaj.org/article/6ebb3290597f46afb1b5429cd5c70271
Publikováno v:
International Review of Social Sciences Research, Vol 3, Iss 2, Pp 1-19 (2023)
This study examined the implementation of Disaster Risk Reduction Management (DRRM) in the 11 Elementary Schools in Santiago District in the Philippines using the Gawad Kalasag criteria. It determined the problems encountered by the schools in the im
Externí odkaz:
https://doaj.org/article/3a8e3e593a0b4922a5ef681bfd2a6977
Publikováno v:
Cognitive Robotics, Vol 3, Iss , Pp 107-126 (2023)
The conventional application of deep reinforcement learning (DRL) to autonomous racing requires the agent to crash during training, thus limiting training to simulation environments. Further, many DRL approaches still exhibit high crash rates after t
Externí odkaz:
https://doaj.org/article/2d471fbdba3b49a785fdb0a94e228b42
Publikováno v:
IEEE Open Journal of Control Systems, Vol 1, Pp 164-179 (2022)
Stability and safety are critical properties for successful deployment of automatic control systems. As a motivating example, consider autonomous mobile robot navigation in a complex environment. A control design that generalizes to different operati
Externí odkaz:
https://doaj.org/article/6b60fdf48bd247e2be7a856ab35d8242
Publikováno v:
IEEE Open Journal of Control Systems, Vol 1, Pp 223-236 (2022)
We present a method for efficiently computing reachable sets and forward invariant sets for continuous-time systems with dynamics that include unknown components. Our main assumption is that, given any hyperrectangle of states, lower and upper bounds
Externí odkaz:
https://doaj.org/article/a618965e950d4478ad03382a3769bb38
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Volker Gabler, Dirk Wollherr
Publikováno v:
Frontiers in Robotics and AI, Vol 9 (2022)
This article focuses on learning manipulation skills from episodic reinforcement learning (RL) in unknown environments using industrial robot platforms. These platforms usually do not provide the required compliant control modalities to cope with unk
Externí odkaz:
https://doaj.org/article/82056ab100d540b192188ce9b99aaa47
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
IEEE Access, Vol 9, Pp 163938-163953 (2021)
Neural Networks (NNs) can provide major empirical performance improvements for closed-loop systems, but they also introduce challenges in formally analyzing those systems’ safety properties. In particular, this work focuses on estimating the forwar
Externí odkaz:
https://doaj.org/article/b7bd72adeec044e5a14587a5672d0e6f