We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
In this paper we formulate the problem of grouping the states of a discrete Markov chain of arbitrary order simultaneously with deconvolving its transition probabilities. As the na...
Abstract. In recent times, the proliferation of spatial data on the Internet is beginning to allow a much larger audience to access and share data currently available in various Ge...
Alberto Belussi, Omar Boucelma, Barbara Catania, Y...
Coevolution has often been based on averaged outcomes, resulting in unstable evaluation. Several theoretical approaches have used archives to provide stable evaluation. However, t...
We investigate a variant of on-line edge-coloring in which there is a fixed number of colors availableandtheaimistocolorasmanyedgesaspossible.Weproveupperandlowerboundsontheperform...