BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Reinforcement Learning for Stochastic Networks\, Toulouse
DTSTART:20240617T070000Z
DTEND:20240621T160000Z
DTSTAMP:20260614T142300Z
UID:indico-event-10541@indico.math.cnrs.fr
DESCRIPTION:Speakers: Céline Comte (CNRS and LAAS)\, Matthieu Jonckheere 
 (LAAS–CNRS)\, Balakrishna Prabhu (LAAS–CNRS)\, Urtzi Ayesta (IRIT–CN
 RS)\, Maaike Verloop (IRIT–CNRS)\n\nTo all participants: Please be aware
  that you will not be able to bring luggage inside the workshop buildings.
  We therefore recommend that you leave your luggage at your hotel.Markov d
 ecisions processes (MDPs) and their model-free counterpart in reinforcemen
 t learning (RL) have known a large success in the last two decades. Althou
 gh research in these two areas has been taking place for more than fifty y
 ears\, the field gained momentum only recently following the advent of pow
 erful hardware and algorithms with which supra-human performance were obta
 ined in games like Chess or Go. However\, these impressive successes often
  rely on quite exceptional hardware possibilities and cannot be applied in
  many “usual” contexts where\, for instance\, the volume of data avail
 able or the amount of computing power is more restricted. To define the ne
 xt generation of more “democratic” and widely applicable algorithms\, 
 such methods still need to deal with very demanding exploration issues as 
 soon as the state/action spaces are not small. One way around this is to u
 se underlying knowledge and structure present in many MDPs. This is especi
 ally true for problems related to scheduling and resource sharing in syste
 ms like server farms\, clouds\, and cellular wireless networks. In recent 
 years\, there has been a huge research effort improving the efficiency of 
 learning algorithms by leveraging the structure of the underlying problem\
 , both in the model-based and model-free frameworks. This workshop will ga
 ther experts and students working at the frontier of this topic.Researcher
 s who wish to present their work at the workshop RL4SN should submit an ab
 stract (for more details see Instructions for Authors). Participants at th
 e conference will be given the opportunity to submit a paper based on thei
 r talk to a special issue of the journal Queueing Systems: Theory and Appl
 ications (QUESTA) (other journals are pending approval). For more details\
 , see the Special Issues page.This workshop is part of the thematic semest
 er Stochastic control and learning for complex networks (SOLACE).\n\nhttps
 ://indico.math.cnrs.fr/event/10541/
LOCATION:ENSEEIHT
URL:https://indico.math.cnrs.fr/event/10541/
END:VEVENT
END:VCALENDAR