Distributed Partially Observable Markov Decision Problems (Distributed POMDPs) are a popular approach for modeling multi-agent systems acting in uncertain domains. Given the signi...
Pradeep Varakantham, Janusz Marecki, Yuichi Yabu, ...
Abstract— A combination of backpropagation and neuroevolution is used to train a neural network visual controller for agents in the Quake II environment. The agents must learn to...
Wireless mesh networks promise to deliver resilient connectivity among network nodes, allowing data to be relayed seamlessly between mobile clients and infrastructure. Routing is ...
Peizhao Hu, Marius Portmann, Ricky Robinson, Jadwi...
The notion of icons in visual environments is limited by perceiving icons as tacit entities that have meaning only to human beings and not to the machines that display them. This ...
—In many scenarios network design is not enforced by a central authority, but arises from the interactions of several self-interested agents. This is the case of the Internet, wh...
Jocelyne Elias, Fabio Martignon, Konstantin Avrach...