: When the user interface is specified, a picture is worth a thousand words, and the worst thing one can do is write a natural-language specification for it. Because this practice ...
The current research presents a system that learns to understand object names, spatial relation terms and event descriptions from observing narrated action sequences. The system e...
Abstract: Classification-based reinforcement learning (RL) methods have recently been proposed as an alternative to the traditional value-function based methods. These methods use...
We consider the problem of incorporating arbitrary preferences in planning systems. A preference may be seen as a goal or constraint that is desirable, but not necessary, to satis...
Most of the straight-forward learning approaches in cooperative robotics imply for each learning robot a state space growth exponential in the number of team members. To remedy the...