|
Student: Frederic Thouin, Ph.D. Student and Richard Thommes, Ph.D.
Supervisor: Prof. Mark Coates
Abstract: Wireless sensor-actuator networks (SANETs), in which nodes perform
actions (actuation) in response to sensor measurements and shared
information, have great potential in medical and agricultural
applications. In this paper, we focus on the problem of using
distributed sensed data to design actuation strategies in order to
elicit a desired response from the environment, whilst attempting to
minimize the communication in the network. Our methodology is based
on batch Q-learning; we describe a distributed approach for learning
dyadic regression trees to estimate the Q-functions from collected
data. Analysis and simulation indicate that (i)substantial
communication savings can be achieved through distributed
learning without significant performance deterioration and (ii)the performance of our technique depends strongly on the amount of training data available.
[Paper (pdf format)]
|