This paper introduces Fuzzy Neural Network controller to increase the ability of a mobile robot in reacting to the dynamic environments. States of robot and environment, for exampl...
We formalize a model for supervised learning of action strategies in dynamic stochastic domains and show that PAC-learning results on Occam algorithms hold in this model as well. W...
We consider the problem of maximizing capacity in a queueing network with flexible servers, where the classes and servers are subject to failure. We assume that the interarrival ...
This paper discusses the use of networks-on-chip (NoCs) consisting of multiple voltage-frequency islands to cope with power consumption, clock distribution and parameter variation...
The application of reinforcement learning algorithms to Partially Observable Stochastic Games (POSG) is challenging since each agent does not have access to the whole state inform...
Alessandro Lazaric, Mario Quaresimale, Marcello Re...