—“AWE” is a programmable “Animated Work Environment” supporting everyday human activities, at home, work and school, in an increasingly digital society. AWE features a no...
Keith Evan Green, Ian D. Walker, Leo J. Gugerty, J...
We present a method of grounded word learning that is powerful enough to learn the meanings of first and second person pronouns. The model uses the understood words in an utteran...
We present a technique for combining audio signal-based music similarity with web-based musical artist similarity to accelerate the task of automatic playlist generation. We demon...
Peter Knees, Tim Pohle, Markus Schedl, Gerhard Wid...
Scalable coordination is a key challenge in deployment of multiagent systems. Resource usage is one part of agent behavior which naturally lends itself to abstraction. CyberOrgs i...
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...