Learning to route efficiently with end-to-end feedback : the value of (identifiable) networked structure
Thesis: S.M., Massachusetts Institute of Technology, Department of Aeronautics and Astronautics, 2018.
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | eng |
| Published: |
Massachusetts Institute of Technology
2019
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/120384 |
| _version_ | 1826195450686865408 |
|---|---|
| author | Zhu, Ruihao, S. M. Massachusetts Institute of Technology |
| author2 | Eytan Modiano. |
| author_facet | Eytan Modiano. Zhu, Ruihao, S. M. Massachusetts Institute of Technology |
| author_sort | Zhu, Ruihao, S. M. Massachusetts Institute of Technology |
| collection | MIT |
| description | Thesis: S.M., Massachusetts Institute of Technology, Department of Aeronautics and Astronautics, 2018. |
| first_indexed | 2024-09-23T10:12:53Z |
| format | Thesis |
| id | mit-1721.1/120384 |
| institution | Massachusetts Institute of Technology |
| language | eng |
| last_indexed | 2024-09-23T10:12:53Z |
| publishDate | 2019 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1203842019-04-12T23:13:47Z Learning to route efficiently with end-to-end feedback : the value of (identifiable) networked structure Zhu, Ruihao, S. M. Massachusetts Institute of Technology Eytan Modiano. Massachusetts Institute of Technology. Department of Aeronautics and Astronautics. Massachusetts Institute of Technology. Department of Aeronautics and Astronautics. Aeronautics and Astronautics. Thesis: S.M., Massachusetts Institute of Technology, Department of Aeronautics and Astronautics, 2018. This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. Cataloged from student-submitted PDF version of thesis. Includes bibliographical references (pages [71]-73). In this thesis, we introduce efficient algorithms which achieve nearly optimal instance-dependent and worst case regrets for the problem of stochastic online shortest path routing with end-to-end feedback. The setting is a natural application of the combinatorial stochastic bandits problem, a special case of the linear stochastic bandits problem. We show how the difficulties posed by the large scale action set can be overcome by the networked structure of the action set. Our approach presents a novel connection between bandit learning and shortest path algorithms. Our main contribution is a series of adaptive exploration algorithms that achieves nearly optimal O ((d²ln(T)+d³) [delta]max=[delta]²min) instance-dependent regret and Õ(d [square root]T) worst case regret at the same time. Driven by the carefully designed Top-Two Comparison (TTC) technique, the algorithms are efficiently implementable. We also conduct extensive numerical experiments to show that our proposed algorithms not only achieve superior regret performances, but also reduce the runtime drastically. by Ruihao Zhu. S.M. 2019-02-14T15:23:10Z 2019-02-14T15:23:10Z 2018 2018 Thesis http://hdl.handle.net/1721.1/120384 1084656754 eng MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission. http://dspace.mit.edu/handle/1721.1/7582 73 pages application/pdf Massachusetts Institute of Technology |
| spellingShingle | Aeronautics and Astronautics. Zhu, Ruihao, S. M. Massachusetts Institute of Technology Learning to route efficiently with end-to-end feedback : the value of (identifiable) networked structure |
| title | Learning to route efficiently with end-to-end feedback : the value of (identifiable) networked structure |
| title_full | Learning to route efficiently with end-to-end feedback : the value of (identifiable) networked structure |
| title_fullStr | Learning to route efficiently with end-to-end feedback : the value of (identifiable) networked structure |
| title_full_unstemmed | Learning to route efficiently with end-to-end feedback : the value of (identifiable) networked structure |
| title_short | Learning to route efficiently with end-to-end feedback : the value of (identifiable) networked structure |
| title_sort | learning to route efficiently with end to end feedback the value of identifiable networked structure |
| topic | Aeronautics and Astronautics. |
| url | http://hdl.handle.net/1721.1/120384 |
| work_keys_str_mv | AT zhuruihaosmmassachusettsinstituteoftechnology learningtorouteefficientlywithendtoendfeedbackthevalueofidentifiablenetworkedstructure |