MDPs are an attractive formalization for planning, but realistic problems often have intractably large state spaces. When we only need a partial policy to get from a fixed start s...
H. Brendan McMahan, Maxim Likhachev, Geoffrey J. G...
Slowdown based on dynamic voltage scaling (DVS) provides the ability to perform an energy-delay tradeoff in the system. Non-preemptive scheduling becomes an integral part of syste...
This paper presents a self-organizing cognitive architecture, known as TD-FALCON, that learns to function through its interaction with the environment. TD-FALCON learns the value ...
Computing systems have become so complex that the IT industry recognizes the necessity of deliberative methods to make these systems self-configuring, self-healing, selfoptimizin...
The MIDAS project is developing infrastructure and policies for optimal display of digital information on devices with diverse characteristics. In this paper we present the prelim...
Unmil Karadkar, Richard Furuta, Jeevan Joseph John...