Reinforcement learning for telescope optimisation

dc.contributor.advisorBassett, Bruce
dc.contributor.authorBlows, Curtly
dc.date.accessioned2020-02-27T13:28:16Z
dc.date.available2020-02-27T13:28:16Z
dc.date.issued2019
dc.date.updated2020-02-27T11:35:34Z
dc.description.abstractReinforcement learning is a relatively new and unexplored branch of machine learning with a wide variety of applications. This study investigates reinforcement learning and provides an overview of its application to a variety of different problems. We then explore the possible use of reinforcement learning for telescope target selection and scheduling in astronomy with the hope of effectively mimicking the choices made by professional astronomers. This is relevant as next-generation astronomy surveys will require near realtime decision making in response to high-speed transient discoveries. We experiment with and apply some of the leading approaches in reinforcement learning to simplified models of the target selection problem. We find that the methods used in this study show promise but do not generalise well. Hence while there are indications that reinforcement learning algorithms could work, more sophisticated algorithms and simulations are needed.
dc.identifier.apacitationBlows, C. (2019). <i>Reinforcement learning for telescope optimisation</i>. (). ,Faculty of Science ,Department of Statistical Sciences. Retrieved from http://hdl.handle.net/11427/31352en_ZA
dc.identifier.chicagocitationBlows, Curtly. <i>"Reinforcement learning for telescope optimisation."</i> ., ,Faculty of Science ,Department of Statistical Sciences, 2019. http://hdl.handle.net/11427/31352en_ZA
dc.identifier.citationBlows, C. 2019. Reinforcement learning for telescope optimisation.en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Blows, Curtly AB - Reinforcement learning is a relatively new and unexplored branch of machine learning with a wide variety of applications. This study investigates reinforcement learning and provides an overview of its application to a variety of different problems. We then explore the possible use of reinforcement learning for telescope target selection and scheduling in astronomy with the hope of effectively mimicking the choices made by professional astronomers. This is relevant as next-generation astronomy surveys will require near realtime decision making in response to high-speed transient discoveries. We experiment with and apply some of the leading approaches in reinforcement learning to simplified models of the target selection problem. We find that the methods used in this study show promise but do not generalise well. Hence while there are indications that reinforcement learning algorithms could work, more sophisticated algorithms and simulations are needed. DA - 2019 DB - OpenUCT DP - University of Cape Town KW - Statistical Sciences LK - https://open.uct.ac.za PY - 2019 T1 - Reinforcement learning for telescope optimisation TI - Reinforcement learning for telescope optimisation UR - http://hdl.handle.net/11427/31352 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/31352
dc.identifier.vancouvercitationBlows C. Reinforcement learning for telescope optimisation. []. ,Faculty of Science ,Department of Statistical Sciences, 2019 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/31352en_ZA
dc.language.rfc3066eng
dc.publisher.departmentDepartment of Statistical Sciences
dc.publisher.facultyFaculty of Science
dc.subjectStatistical Sciences
dc.titleReinforcement learning for telescope optimisation
dc.typeMaster Thesis
dc.type.qualificationlevelMasters
dc.type.qualificationnameMSc
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
thesis_sci_2019_blows_curtly.pdf
Size:
5.64 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
0 B
Format:
Item-specific license agreed upon to submission
Description:
Collections