人工智能论文20230325 2020PhD Stanford Control, filtering, learning, and multi-robot algorithms for large graph-based Markov decision processes.pdfVIP

©2020byRaviHaksar.AllRightsReserved.

Re-distributedbyStanfordUniversityunderlicensewiththeauthor.

ThisworkislicensedunderaCreativeCommonsAttribution-

Noncommercial3.0UnitedStatesLicense.

/licenses/by-nc/3.0/us/

Thisdissertationisonlineat:/hr193tr6765

ii

IcertifythatIhavereadthisdissertationandthat,inmyopinion,itisfullyadequate

inscopeandqualityasadissertationforthedegreeofDoctorofPhilosophy.

MacSchwager,PrimaryAdviser

IcertifythatIhavereadthisdissertationandthat,inmyopinion,itisfullyadequate

inscopeandqualityasadissertationforthedegreeofDoctorofPhilosophy.

AllisonOkamura,Co-Adviser

IcertifythatIhavereadthisdissertationandthat,inmyopinion,itisfullyadequate

inscopeandqualityasadissertationforthedegreeofDoctorofPhilosophy.

MykelKochenderfer

IcertifythatIhavereadthisdissertationandthat,inmyopinion,itisfullyadequate

inscopeandqualityasadissertationforthedegreeofDoctorofPhilosophy.

BenjaminVanRoy

ApprovedfortheStanfordUniversityCommitteeonGraduateStudies.

StaceyF.Bent,ViceP