1 Search Results for "Appavoo, Anuja Meetoo"


Document
Track C: Foundations of Networks and Multi-Agent Systems: Models, Algorithms and Information Management
Periodic Bandits and Wireless Network Selection

Authors: Shunhao Oh, Anuja Meetoo Appavoo, and Seth Gilbert

Published in: LIPIcs, Volume 132, 46th International Colloquium on Automata, Languages, and Programming (ICALP 2019)


Abstract
Bandit-style algorithms have been studied extensively in stochastic and adversarial settings. Such algorithms have been shown to be useful in multiplayer settings, e.g. to solve the wireless network selection problem, which can be formulated as an adversarial bandit problem. A leading bandit algorithm for the adversarial setting is EXP3. However, network behavior is often repetitive, where user density and network behavior follow regular patterns. Bandit algorithms, like EXP3, fail to provide good guarantees for periodic behaviors. A major reason is that these algorithms compete against fixed-action policies, which is ineffective in a periodic setting. In this paper, we define a periodic bandit setting, and periodic regret as a better performance measure for this type of setting. Instead of comparing an algorithm’s performance to fixed-action policies, we aim to be competitive with policies that play arms under some set of possible periodic patterns F (for example, all possible periodic functions with periods 1,2,*s,P). We propose Periodic EXP4, a computationally efficient variant of the EXP4 algorithm for periodic settings. With K arms, T time steps, and where each periodic pattern in F is of length at most P, we show that the periodic regret obtained by Periodic EXP4 is at most O(sqrt{PKT log K + KT log |F|}). We also prove a lower bound of Omega (sqrt{PKT + KT {log |F|}/{log K}}) for the periodic setting, showing that this is optimal within log-factors. As an example, we focus on the wireless network selection problem. Through simulation, we show that Periodic EXP4 learns the periodic pattern over time, adapts to changes in a dynamic environment, and far outperforms EXP3.

Cite as

Shunhao Oh, Anuja Meetoo Appavoo, and Seth Gilbert. Periodic Bandits and Wireless Network Selection. In 46th International Colloquium on Automata, Languages, and Programming (ICALP 2019). Leibniz International Proceedings in Informatics (LIPIcs), Volume 132, pp. 149:1-149:15, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)


Copy BibTex To Clipboard

@InProceedings{oh_et_al:LIPIcs.ICALP.2019.149,
  author =	{Oh, Shunhao and Appavoo, Anuja Meetoo and Gilbert, Seth},
  title =	{{Periodic Bandits and Wireless Network Selection}},
  booktitle =	{46th International Colloquium on Automata, Languages, and Programming (ICALP 2019)},
  pages =	{149:1--149:15},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-109-2},
  ISSN =	{1868-8969},
  year =	{2019},
  volume =	{132},
  editor =	{Baier, Christel and Chatzigiannakis, Ioannis and Flocchini, Paola and Leonardi, Stefano},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ICALP.2019.149},
  URN =		{urn:nbn:de:0030-drops-107251},
  doi =		{10.4230/LIPIcs.ICALP.2019.149},
  annote =	{Keywords: multi-armed bandits, wireless network selection, periodicity in environment}
}
  • Refine by Author
  • 1 Appavoo, Anuja Meetoo
  • 1 Gilbert, Seth
  • 1 Oh, Shunhao

  • Refine by Classification
  • 1 Theory of computation → Online learning algorithms

  • Refine by Keyword
  • 1 multi-armed bandits
  • 1 periodicity in environment
  • 1 wireless network selection

  • Refine by Type
  • 1 document

  • Refine by Publication Year
  • 1 2019

Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail