Efficient Reinforcement Learning using Gaussian Processes
This book examines Gaussian processes in both model-based reinforcement learning (RL) and inference in nonlinear dynamic systems.First, we introduce PILCO, a fully Bayesian approach for efficient RL in continuous-valued state and action spaces when no expert knowledge is available. PILCO takes model...
- Autores:
- Tipo de recurso:
- Book
- Fecha de publicación:
- 2010
- Institución:
- Universidad de Bogotá Jorge Tadeo Lozano
- Repositorio:
- Expeditio: repositorio UTadeo
- Idioma:
- eng
- OAI Identifier:
- oai:expeditiorepositorio.utadeo.edu.co:20.500.12010/17578
- Acceso en línea:
- https://directory.doabooks.org/handle/20.500.12854/45907
http://hdl.handle.net/20.500.12010/17578
- Palabra clave:
- Autonomous learning
Gaussian processes
Machine learning
Aprendizaje
Aprendizaje experiencial
Aptitud de aprendizaje
- Rights
- License
- Abierto (Texto Completo)
| id |
UTADEO2_1976428ecc47f2a133657d6389e34ba8 |
|---|---|
| oai_identifier_str |
oai:expeditiorepositorio.utadeo.edu.co:20.500.12010/17578 |
| network_acronym_str |
UTADEO2 |
| network_name_str |
Expeditio: repositorio UTadeo |
| repository_id_str |
|
| dc.title.spa.fl_str_mv |
Efficient Reinforcement Learning using Gaussian Processes |
| title |
Efficient Reinforcement Learning using Gaussian Processes |
| spellingShingle |
Efficient Reinforcement Learning using Gaussian Processes Autonomous learning Gaussian processes Machine learning Aprendizaje Aprendizaje experiencial Aptitud de aprendizaje |
| title_short |
Efficient Reinforcement Learning using Gaussian Processes |
| title_full |
Efficient Reinforcement Learning using Gaussian Processes |
| title_fullStr |
Efficient Reinforcement Learning using Gaussian Processes |
| title_full_unstemmed |
Efficient Reinforcement Learning using Gaussian Processes |
| title_sort |
Efficient Reinforcement Learning using Gaussian Processes |
| dc.subject.spa.fl_str_mv |
Autonomous learning Gaussian processes Machine learning |
| topic |
Autonomous learning Gaussian processes Machine learning Aprendizaje Aprendizaje experiencial Aptitud de aprendizaje |
| dc.subject.lemb.spa.fl_str_mv |
Aprendizaje Aprendizaje experiencial Aptitud de aprendizaje |
| description |
This book examines Gaussian processes in both model-based reinforcement learning (RL) and inference in nonlinear dynamic systems.First, we introduce PILCO, a fully Bayesian approach for efficient RL in continuous-valued state and action spaces when no expert knowledge is available. PILCO takes model uncertainties consistently into account during long-term planning to reduce model bias. Second, we propose principled algorithms for robust filtering and smoothing in GP dynamic systems. |
| publishDate |
2010 |
| dc.date.created.none.fl_str_mv |
2010 |
| dc.date.accessioned.none.fl_str_mv |
2021-02-22T17:35:19Z |
| dc.date.available.none.fl_str_mv |
2021-02-22T17:35:19Z |
| dc.type.coar.spa.fl_str_mv |
http://purl.org/coar/resource_type/c_2f33 |
| format |
http://purl.org/coar/resource_type/c_2f33 |
| dc.identifier.isbn.none.fl_str_mv |
9783866445697 |
| dc.identifier.other.none.fl_str_mv |
https://directory.doabooks.org/handle/20.500.12854/45907 |
| dc.identifier.uri.none.fl_str_mv |
http://hdl.handle.net/20.500.12010/17578 |
| dc.identifier.doi.none.fl_str_mv |
10.5445/KSP/1000019799 |
| identifier_str_mv |
9783866445697 10.5445/KSP/1000019799 |
| url |
https://directory.doabooks.org/handle/20.500.12854/45907 http://hdl.handle.net/20.500.12010/17578 |
| dc.language.iso.spa.fl_str_mv |
eng |
| language |
eng |
| dc.rights.coar.fl_str_mv |
http://purl.org/coar/access_right/c_abf2 |
| dc.rights.local.spa.fl_str_mv |
Abierto (Texto Completo) |
| dc.rights.creativecommons.none.fl_str_mv |
https://creativecommons.org/licenses/by-nc-nd/4.0/ |
| rights_invalid_str_mv |
Abierto (Texto Completo) https://creativecommons.org/licenses/by-nc-nd/4.0/ http://purl.org/coar/access_right/c_abf2 |
| dc.format.extent.spa.fl_str_mv |
IX, 205 páginas |
| dc.format.mimetype.spa.fl_str_mv |
application/pdf |
| dc.publisher.spa.fl_str_mv |
KIT Scientific Publishing |
| institution |
Universidad de Bogotá Jorge Tadeo Lozano |
| bitstream.url.fl_str_mv |
https://expeditiorepositorio.utadeo.edu.co/bitstream/20.500.12010/17578/1/978-3-86644-569-7_pdfa.pdf https://expeditiorepositorio.utadeo.edu.co/bitstream/20.500.12010/17578/2/license.txt https://expeditiorepositorio.utadeo.edu.co/bitstream/20.500.12010/17578/3/978-3-86644-569-7_pdfa.pdf.jpg |
| bitstream.checksum.fl_str_mv |
c88f0ebdb408c3e832898eaffe127dc5 abceeb1c943c50d3343516f9dbfc110f d2ebd88c86586ec1931d8ddf1771cbf1 |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio Institucional - Universidad Jorge Tadeo Lozano |
| repository.mail.fl_str_mv |
expeditio@utadeo.edu.co |
| _version_ |
1808495304967716864 |
| spelling |
2021-02-22T17:35:19Z2021-02-22T17:35:19Z20109783866445697https://directory.doabooks.org/handle/20.500.12854/45907http://hdl.handle.net/20.500.12010/1757810.5445/KSP/1000019799This book examines Gaussian processes in both model-based reinforcement learning (RL) and inference in nonlinear dynamic systems.First, we introduce PILCO, a fully Bayesian approach for efficient RL in continuous-valued state and action spaces when no expert knowledge is available. PILCO takes model uncertainties consistently into account during long-term planning to reduce model bias. Second, we propose principled algorithms for robust filtering and smoothing in GP dynamic systems.IX, 205 páginasapplication/pdfengKIT Scientific PublishingAutonomous learningGaussian processesMachine learningAprendizajeAprendizaje experiencialAptitud de aprendizajeEfficient Reinforcement Learning using Gaussian ProcessesAbierto (Texto Completo)https://creativecommons.org/licenses/by-nc-nd/4.0/http://purl.org/coar/access_right/c_abf2http://purl.org/coar/resource_type/c_2f33Deisenroth, Marc PeterORIGINAL978-3-86644-569-7_pdfa.pdf978-3-86644-569-7_pdfa.pdfVer documentoapplication/pdf5639599https://expeditiorepositorio.utadeo.edu.co/bitstream/20.500.12010/17578/1/978-3-86644-569-7_pdfa.pdfc88f0ebdb408c3e832898eaffe127dc5MD51open accessLICENSElicense.txtlicense.txttext/plain; charset=utf-82938https://expeditiorepositorio.utadeo.edu.co/bitstream/20.500.12010/17578/2/license.txtabceeb1c943c50d3343516f9dbfc110fMD52open accessTHUMBNAIL978-3-86644-569-7_pdfa.pdf.jpg978-3-86644-569-7_pdfa.pdf.jpgIM Thumbnailimage/jpeg11207https://expeditiorepositorio.utadeo.edu.co/bitstream/20.500.12010/17578/3/978-3-86644-569-7_pdfa.pdf.jpgd2ebd88c86586ec1931d8ddf1771cbf1MD53open access20.500.12010/17578oai:expeditiorepositorio.utadeo.edu.co:20.500.12010/175782021-02-22 12:36:41.117open accessRepositorio Institucional - Universidad Jorge Tadeo Lozanoexpeditio@utadeo.edu.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 |