[Lisa_seminaires] REMINDER: UdeM-McGill-MITACS machine learning seminar Tues April 8th, 10am, MC103 - NEW LOCATION

Hugo Larochelle larocheh at iro.umontreal.ca
Lun 7 Avr 08:59:46 EDT 2008


This week's seminar (see http://www.iro.umontreal.ca/article.php3? 
id_article=107&lang=en):


Aggregate Markov Decision Processes


by Hasan Mirza,
McGill University

Location: McConnell Engineering (McGill), room 103
Time: April 8th 2008, 10am

We consider a special type of Markov decision problem in which an
agent maintains an infiitely divisible collection of identical
"machines," each described by a standard finite-state MDP. The agent
is subject to constraints on fraction of the machines receiving each
available action. We model the collection of MDPs as a single MDP by
looking at the frequency at which each state is observed in each
underlying MDP. Although this MDP has continuous state and action
spaces, its transitions are deterministic, and its structure leads to
interesting properties such as a convex value function. We present a
linear-programming receding-horizon control technique for use under
the discountedcost performance criterion, and investigate its
behaviour through experiments on example problems. The experimental
results show that the technique is viable on practically-sized
problems. Finally, we present a probabilistic result that relates the
frequency MDP to the model where each machine is treated separately
and the collection is not infinitely divisible.



Plus d'informations sur la liste de diffusion Lisa_seminaires