Model-Based Bayesian Sparse Sampling for Data Efficient Control

dc.contributor.authorTse, Timmy Rong Tian
dc.date.accessioned2019-06-24T18:34:15Z
dc.date.available2019-06-24T18:34:15Z
dc.date.issued2019-06-24
dc.date.submitted2019-06-14
dc.description.abstractIn this work, we propose a novel Bayesian-inspired model-based policy search algorithm for data efficient control. In contrast to other model-based approaches, our algorithm makes use of approximate Gaussian processes in the form of random Fourier features for fast online systems identification and computationally efficient posterior updates via rank one Cholesky updates. Furthermore, fast and tractable posterior updates permits policy optimization to leverage knowledge from posterior evolution tracking for a directed Bayesian approach to the exploration-exploitation dilemma. To address the optimization formulation involving belief monitoring as well as the potentiality of a loss surface with zero gradients everywhere, we leverage a blackbox optimizer in the form of covariance matrix adaptation evolution strategy (CMA-ES). We test our algorithm on four challenging control tasks and report the superior data efficiency as well as the exploration capabilities of our model.en
dc.identifier.urihttp://hdl.handle.net/10012/14774
dc.language.isoenen
dc.pendingfalse
dc.publisherUniversity of Waterlooen
dc.subjectmachine learningen
dc.subjectreinforcement learningen
dc.subjectartificial intelligenceen
dc.titleModel-Based Bayesian Sparse Sampling for Data Efficient Controlen
dc.typeMaster Thesisen
uws-etd.degreeMaster of Mathematicsen
uws-etd.degree.departmentDavid R. Cheriton School of Computer Scienceen
uws-etd.degree.disciplineComputer Scienceen
uws-etd.degree.grantorUniversity of Waterlooen
uws.contributor.advisorPoupart, Pascal
uws.contributor.advisorLaw, Edith
uws.contributor.affiliation1Faculty of Mathematicsen
uws.peerReviewStatusUnrevieweden
uws.published.cityWaterlooen
uws.published.countryCanadaen
uws.published.provinceOntarioen
uws.scholarLevelGraduateen
uws.typeOfResourceTexten

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Tse_TimmyRongTian.pdf
Size:
2.2 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
6.08 KB
Format:
Item-specific license agreed upon to submission
Description: