Published September 24, 2019
| Version v1
Conference paper
A learning algorithm for the Whittle index policy for scheduling web crawlers
- Creators
- Avrachenkov, Konstantin
- Borkar, Vivek
- Others:
- Network Engineering and Operations (NEO ) ; Inria Sophia Antipolis - Méditerranée (CRISAM) ; Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)
- Department of Electrical Engineering [IIT-Bombay] (EE-IIT) ; Indian Institute of Technology Kanpur (IIT Kanpur)
- The authors were supported in part by theINRIA-DST project 'Machine Learning for Net-work Analytics' administered by the Indo-FrenchCentre for Promotion of Advanced Research(IFCPAR). VB was also supported by a J. C.Bose Fellowship from the Government of In-dia. The work of KA is also supported by thePIA ANSWER project PIA FSN2 no.P159564-2661789/DOS0060094 between Inria and Qwant.
Description
We revisit the Whittle index policy for scheduling web crawlers for ephemeral content proposed in Avrachenkov and Borkar, IEEE Trans. Control of Network Systems 5(1), 2016, and develop a reinforcement learning scheme for it based on LSPE(0). The scheme leverages the known structural properties of the Whittle index policy.
Abstract
International audience
Additional details
- URL
- https://hal.inria.fr/hal-02416599
- URN
- urn:oai:HAL:hal-02416599v1
- Origin repository
- UNICA