Please use this identifier to cite or link to this item:
https://scholarbank.nus.edu.sg/handle/10635/182565
DC Field | Value | |
---|---|---|
dc.title | REVISED APPROACH FOR RISK-AVERSE MULTI-ARMED BANDITS UNDER CVAR CRITERIA | |
dc.contributor.author | NAJAKORN KHAJONCHOTPANYA | |
dc.date.accessioned | 2020-10-31T18:01:02Z | |
dc.date.available | 2020-10-31T18:01:02Z | |
dc.date.issued | 2020-07-08 | |
dc.identifier.citation | NAJAKORN KHAJONCHOTPANYA (2020-07-08). REVISED APPROACH FOR RISK-AVERSE MULTI-ARMED BANDITS UNDER CVAR CRITERIA. ScholarBank@NUS Repository. | |
dc.identifier.uri | https://scholarbank.nus.edu.sg/handle/10635/182565 | |
dc.description.abstract | Multi-armed bandits (MAB) is a well-known online learning framework for balancing the trade-off between exploration and exploitation inherent in sequential decision problems. In the classical MAB setting, a metric for measuring the performance is a sample mean of the actualised rewards, which considered a risk-neutral objective. However, various applications, e.g., clinical trials, finance, a risk-sensitive objective is more desired. Thus, this thesis incorporates conditional value at risk, which is a widely-used risk measure, into the MAB problems. Particularly, this thesis proposes a new variant of the upper confidence bound algorithm, and establishes its regret bounds with respect to different regret notions proposed in the risk-averse MAB literature. Finally, this thesis conducts a theoretical analysis and a numerical experiment comparing the proposed algorithm’s performance with the other state-of-the-art algorithms, and concludes that the proposed algorithm performs competitively against the other state-of-the-art algorithms. | |
dc.language.iso | en | |
dc.subject | Multi-armed bandits, Online learning, Upper confidence bound, Risk awareness, Risk aversion, Conditional value at risk | |
dc.type | Thesis | |
dc.contributor.department | INST OF OPERATIONS RESEARCH & ANALYTICS | |
dc.contributor.supervisor | Napat Rujeerapaiboon | |
dc.contributor.supervisor | Beng Lim Andrew Ee | |
dc.description.degree | Master's | |
dc.description.degreeconferred | MASTER OF SCIENCE (RSH-IORA) | |
Appears in Collections: | Master's Theses (Open) |
Show simple item record
Files in This Item:
File | Description | Size | Format | Access Settings | Version | |
---|---|---|---|---|---|---|
KhajonchotpanyaN.pdf | 713.43 kB | Adobe PDF | OPEN | None | View/Download |
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.