Zobrazeno 1 - 10
of 42
pro vyhledávání: '"Carl Edward Rasmussen"'
Autor:
Yen-Chen Wu, Carl Edward Rasmussen
Publikováno v:
NAACL-HLT
Training dialogue agents requires a large number of interactions with users: agents have no idea about which responses are bad among a lengthy dialogue. In this paper, we propose loop-clipping policy optimisation (LCPO) to eliminate useless responses
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bad5306c76944c37bc5e364a88e4bba9
https://doi.org/10.18653/v1/2021.naacl-main.267
https://doi.org/10.18653/v1/2021.naacl-main.267
Techniques known as Nonlinear Set Membership prediction or Lipschitz Interpolation are approaches to supervised machine learning that utilise presupposed Lipschitz properties to perform inference over unobserved function values. Provided a bound on t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::689983e1ce6df7df0c8eefcaeb319e47
Publikováno v:
ICASSP
By interacting with human and learning from reward signals, reinforcement learning is an ideal way to build conversational AI. Concerning the expenses of real-users’ responses, improving sample-efficiency has been the key issue when applying reinfo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::da2f2d7c28a8709aabe2dd79fac58563
https://doi.org/10.1109/icassp40776.2020.9053235
https://doi.org/10.1109/icassp40776.2020.9053235
Publikováno v:
Proceedings of the ASME 2020 Turbomachinery Technical Conference Exposition
Experiments are performed on a turbulent swirling flame placed inside a vertical tube whose fundamental acoustic mode becomes unstable at higher powers and equivalence ratios. The power, equivalence ratio, fuel composition and boundary condition of t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::99e2a530ab9cb25fd60c6f78babb9ab7
https://doi.org/10.31224/osf.io/ysgp4
https://doi.org/10.31224/osf.io/ysgp4
Publikováno v:
ECC
Methods known as Lipschitz Interpolation or Nonlinear Set Membership regression have become established tools for nonparametric system-identification and data-based control. They utilise presupposed Lipschitz properties to compute inferences over uno
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::593742a6f7e9c9852045a4a525f0ee62
https://doi.org/10.23919/ecc.2018.8550439
https://doi.org/10.23919/ecc.2018.8550439
Autor:
Carl Edward Rasmussen, Ryan Turner
Publikováno v:
Neurocomputing. 80:47-53
The unscented Kalman filter (UKF) is a widely used method in control and time series applications. The UKF suffers from arbitrary parameters necessary for a step known as sigma point placement, causing it to perform poorly in nonlinear problems. We s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c28fecce034cc95d652c4132a5176ff0
https://doi.org/10.1016/j.neucom.2011.07.029
https://doi.org/10.1016/j.neucom.2011.07.029
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 37(2)
Autonomous learning has been a promising direction in control and robotics for more than a decade since data-driven learning allows to reduce the amount of engineering knowledge, which is otherwise required. However, autonomous reinforcement learning
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c937286a0b4966a84d27844ea7916307
https://pubmed.ncbi.nlm.nih.gov/26353251
https://pubmed.ncbi.nlm.nih.gov/26353251
Publikováno v:
IFAC Proceedings Volumes
Nonparametric Gaussian Process models, a Bayesian statistics approach, are used to implement a nonlinear adaptive control law. Predictions, including propagation of the state uncertainty are made over a K-step horizon. The expected value of a quadrat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8c88abb3664bf329471769b097cca5ac
https://doi.org/10.1016/s1474-6670(17)34915-7
https://doi.org/10.1016/s1474-6670(17)34915-7
Autor:
Marc Peter Deisenroth, Duy Nguyen-Tuong, H. van Hoof, Carl Edward Rasmussen, Alois Knoll, A. McHutchon, Jan Peters, Bastian Bischoff
Publikováno v:
ICRA
2014 IEEE International Conference on Robotics and Automation (ICRA 2014)
Hong Kong, China
2014 IEEE International Conference on Robotics and Automation (ICRA 2014)
Hong Kong, China
© 2014 IEEE. In many complex robot applications, such as grasping and manipulation, it is difficult to program desired task solutions beforehand, as robots are within an uncertain and dynamic environment. In such cases, learning tasks from experienc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::09440babef9ecc7f02556b1b77a30ba1
https://doi.org/10.1109/icra.2014.6907422
https://doi.org/10.1109/icra.2014.6907422
Gaussian process state-space models (GP-SSMs) are a very exible family of models of nonlinear dynamical systems. They comprise a Bayesian nonparametric representation of the dynamics of the system and additional (hyper-)parameters governing the prope
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4ed5904a369c16b740237989d37daf07
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-110058
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-110058