Our focus is on designing adaptable agents for highly dynamic environments. Wehave implementeda reinforcement learning architecture as the reactive componentof a twolayer control ...
Abstract. We study two boosting algorithms, Coordinate Ascent Boosting and Approximate Coordinate Ascent Boosting, which are explicitly designed to produce maximum margins. To deri...
Cynthia Rudin, Robert E. Schapire, Ingrid Daubechi...
This paper introduces AORTA, a software architecture that provides object-level coordination and shared workspace awareness support to synchronous and distributed collaborative app...
Most research about multi-agent coordination is concentrated at a high level, e.g., developing coordination interaction protocols to be imposed on agents. There has been less conc...
This work presents some anticipatory mechanisms in an agent architecture, modeling affective behaviours as effects of surprise. Through experiment discussion, the advantages of bec...