Abstract. Imitative learning can be considered an essential task of humans development. People use instructions and demonstrations provided by other human experts to acquire knowle...
Grazia Bombini, Nicola Di Mauro, Teresa Maria Alto...
In this paper we present RETALIATE, an online reinforcement learning algorithm for developing winning policies in team firstperson shooter games. RETALIATE has three crucial chara...
In this paper, we first discuss the meaning of physical embodiment and the complexity of the environment in the context of multi-agent learning. We then propose a vision-based rei...
This work employs data mining algorithms to discover visual entities that are strongly associated to autonomously discovered modes of action, in an embodied agent. Mappings are lea...
Video games provide a rich testbed for artificial intelligence methods. In particular, creating automated opponents that perform well in strategy games is a difficult task. For in...