Brainstormers 3D { Team Description 2005
Marc Halbrand Arne Voigtlander · 2005
The main interest behind the Brainstormers' eort in the robocup soccer domain is to develop and to apply machine learning tech- niques in complex domains. Especially, we are interested in reinforcement learning methods, where the training signal is only given in terms of suc- cess or failure. Our nal goal is a learning system, where we only plug in 'win the match' { and our agents learn to generate the appropriate behaviour. As the server for the 2005 competition is not yet nished, this paper mostly describes changes since 2004 in the architecture of the Brainstormers3d team and the self-localization.