Zobrazeno 1 - 10
of 33
pro vyhledávání: '"Todd Hester"'
Autor:
Daniel J. Mankowitz, Cosmin Paduraru, Gabriel Dulac-Arnold, Nir Levine, Jerry Li, Todd Hester, Sven Gowal
Publikováno v:
Machine Learning. 110:2419-2468
Reinforcement learning (RL) has proven its worth in a series of artificial domains, and is beginning to show some successes in real-world scenarios. However, much of the research advances in RL are hard to leverage in real-world systems due to a seri
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::48400b369d20140e3d3fb921d47b7dd2
https://doi.org/10.1007/s10994-021-05961-4
https://doi.org/10.1007/s10994-021-05961-4
Autor:
Brett Wiltshire, Marc Nunkesser, Zhongwen Xu, Xueying Guo, Austin Derrow-Pinion, Ang Li, David Wong, Alvaro Sanchez-Gonzalez, Peter W. Battaglia, Vishal Gupta, Yujia Li, Seongjae Lee, Jennifer She, Todd Hester, Oliver Fritz Lange, Petar Veličković, Luis Perez
Publikováno v:
CIKM
Travel-time prediction constitutes a task of high importance in transportation networks, with web mapping services like Google Maps regularly serving vast quantities of travel time queries from users and enterprises alike. Further, such a task requir
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bae04b9a2593497fc27d70d42e4c43af
http://arxiv.org/abs/2108.11482
http://arxiv.org/abs/2108.11482
Autor:
Peter Stone, Todd Hester
Publikováno v:
Artificial Intelligence. 247:170-186
Reinforcement Learning (RL) agents are typically deployed to learn a specific, concrete task based on a pre-defined reward function. However, in some cases an agent may be able to gain experience in the domain prior to being given a task. In such cas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::01ddbe75f02898b3d963809cfcb2006b
https://doi.org/10.1016/j.artint.2015.05.002
https://doi.org/10.1016/j.artint.2015.05.002
Publikováno v:
ICRA
Insertion is a challenging haptic and visual control problem with significant practical value for manufacturing. Existing approaches in the model-based robotics community can be highly effective when task geometry is known, but are complex and cumber
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::27bae9167de470a3646f2f45d7f047ff
http://arxiv.org/abs/1810.01531
http://arxiv.org/abs/1810.01531
Autor:
Todd Hester, Matej Vecerik, Olivier Pietquin, Marc Lanctot, Tom Schaul, Bilal Piot, Dan Horgan, John Quan, Andrew Sendonaris, Ian Osband, Gabriel Dulac-Arnold, John Agapiou, Joel Leibo, Audrunas Gruslys
Deep reinforcement learning (RL) has achieved several high profile successes in difficult decision-making problems. However, these algorithms typically require a huge amount of data before they reach reasonable performance. In fact, their performance
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d2603999dd3fc6b0bb5f7dadefd67bf1
http://arxiv.org/abs/1704.03732
http://arxiv.org/abs/1704.03732
Autor:
Peter Stone, Todd Hester
Publikováno v:
Machine Learning. 90:385-429
The use of robots in society could be expanded by using reinforcement learning (RL) to allow robots to learn and adapt to new situations online. RL is a paradigm for learning sequential decision making tasks, usually formulated as a Markov Decision P
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::36e181932b76393c4a1d63209a1d8a5d
https://doi.org/10.1007/s10994-012-5322-7
https://doi.org/10.1007/s10994-012-5322-7
Publikováno v:
Proceedings of the IEEE. 98:450-461
Quantitative assessment of motor abilities in stroke survivors can provide valuable feedback to guide clinical interventions. Numerous clinical scales were developed in the past to assess levels of impairment and functional limitation in individuals
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b876e5af4b8f2b3fac9bedfb1a996088
https://doi.org/10.1109/jproc.2009.2038727
https://doi.org/10.1109/jproc.2009.2038727
Autor:
S. Patei, Alice W. Flaherty, Paolo Bonato, John H. Growdon, Todd Hester, N. Huggins, Richard Hughes, David G. Standaert
Publikováno v:
IEEE Pervasive Computing. 7:56-61
Our study suggests that a sensor-based technique might be an important adjunct to existing clinical measures to improve the management of patients undergoing Parkinson's control therapy via deep-brain stimulation. In the future, clinicians could gath
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::58dcf46e95d22ecf72fff6945508903d
https://doi.org/10.1109/mprv.2008.15
https://doi.org/10.1109/mprv.2008.15
Autor:
Todd Hester
This book presents and develops new reinforcement learning methods that enable fast and robust learning on robots in real-time.Robots have the potential to solve many problems in society, because of their ability to work in dangerous places doing nec
Autor:
Todd Hester, Peter Stone
Publikováno v:
RoboCup 2013: Robot World Cup XVII ISBN: 9783662444672
RoboCup
RoboCup
The use of robots in society could be expanded by using reinforcement learning (RL) to allow robots to learn and adapt to new situations on-line. RL is a paradigm for learning sequential decision making tasks, usually formulated as a Markov Decision
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::acad410783f52c878c3593f5c2ece14d
https://doi.org/10.1007/978-3-662-44468-9_47
https://doi.org/10.1007/978-3-662-44468-9_47