Despite the recent advances in planning with MDPs, the problem of generating good policies is still hard. This paper describes a way to generate policies in MDPs by (1) determiniz...
There is a number of recent research lines addressing complex negotiations in highly rugged utility spaces. However, most of them focus on overcoming the problems imposed by the c...
Hybrid systems such as those that combine 3D virtual worlds and organization based multiagent systems add new visual and communication features for multi-user applications. The des...
Tomas Trescak, Marc Esteva, Inmaculada Rodrí...
This paper concerns the problem of agent trust in an electronic market place. We maintain that agent trust involves making decisions under uncertainty and therefore the phenomenon...
PAC-MDP algorithms approach the exploration-exploitation problem of reinforcement learning agents in an effective way which guarantees that with high probability, the algorithm pe...
We introduce the novel problem of inter-robot transfer learning for perceptual classification of objects, where multiple heterogeneous robots communicate and transfer learned obje...