We model reinforcement learning as the problem of learning to control a Partially Observable Markov Decision Process ( ¢¡¤£¦¥§ ), and focus on gradient ascent approache...
—Scientific simulation and modeling often aid in making critical decisions in such diverse fields as city planning, severe weather prediction and influenza modeling. In some o...
In the design of resource bounded agents, high-level cognitive activities, such as reasoning, raise important problems related both to the adaptive ability and to the computationa...
— Quality of Service (QoS) is an area with high academic curiosity. Our long-term goal is to develop a unified mathematical model. This paper is a first step towards this ambit...
In this paper, we consider the effects on network capacity when the nodes of an ad hoc network are allowed to cooperate. These results are then compared to the theoretical upper b...