This paper shows how universal learning can be achieved with expert advice. To this aim, we specify an experts algorithm with the following characteristics: (a) it uses only feedba...
Reinforcement learning (RL) was originally proposed as a framework to allow agents to learn in an online fashion as they interact with their environment. Existing RL algorithms co...
Pascal Poupart, Nikos A. Vlassis, Jesse Hoey, Kevi...
Multi-Agent Plan Recognition (MAPR) seeks to identify the dynamic team structures and team behaviors from the observations of the activity-sequences of a set of intelligent agents...
A central problem in artificial intelligence is to choose actions to maximize reward in a partially observable, uncertain environment. To do so, we must learn an accurate model of ...
Many applications of networks of agents, including mobile sensor networks, unmanned air vehicles, autonomous underwater vehicles, involve 100s of agents acting collaboratively und...
Janusz Marecki, Tapana Gupta, Pradeep Varakantham,...