Our purpose is to study how different muscles collaborate together to efficiently create a smooth, coordinated reaching movement. In the EMG literature, it has been commonplace to...
Information-based agency is founded on two observations: everything in an agent’s world model is uncertain, and everything that an agent communicates gives away valuable informa...
We examine the relationship between the predictions made by different learning algorithms and true posterior probabilities. We show that maximum margin methods such as boosted tre...
Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial...
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...