Abstract—Networks cannot be managed without communication among geographically distributed network devices and control agents. Unfortunately, computer networks today lack an auto...
Hemant Gogineni, Albert G. Greenberg, David A. Mal...
This paper studies the deviations of the regret in a stochastic multi-armed bandit problem. When the total number of plays n is known beforehand by the agent, Audibert et al. (2009...
A traditional goal of Artificial Intelligence research has been a system that can read unrestricted natural language texts on a given topic, build a model of that topic and reason...
Ken Barker, Bhalchandra Agashe, Shaw Yi Chaw, Jame...
— “Word-of-Mouth”, a novel scheme for sharing the service quality experienced with different local networks, is presented and evaluated as a distributed solution for performi...
Decentralized MDPs provide powerful models of interactions in multi-agent environments, but are often very difficult or even computationally infeasible to solve optimally. Here we...