A three-level functional architecture for a team of mobile robots is described in detail, including the de nition of the role assigned to each level, the main concepts involved, a...
Pedro U. Lima, Rodrigo M. M. Ventura, Pedro Apar&i...
Coordinated action for a team of robots is a challenging problem, especially in dynamic, unpredictable environments. Robot soccer is an instance of a domain where well defined goa...
Michael H. Bowling, Brett Browning, Manuela M. Vel...
We use reinforcement learning (RL) to compute strategies for multiagent soccer teams. RL may pro t signi cantly from world models (WMs) estimating state transition probabilities an...
The paper describes the architecture and the scientific goals of the virtual soccer team “AT Humboldt 99”, which is the successor of vice champion “AT Humboldt 98” from Ro...
Hans-Dieter Burkhard, Jan Wendler, Thomas Meinert,...
We use simulated soccer to study multiagent learning. Each team's players (agents) share action set and policy, but may behave di erently due to position-dependent inputs. All...