We show that states of a dynamical system can be usefully represented by multi-step, action-conditional predictions of future observations. State representations that are grounded...
Michael L. Littman, Richard S. Sutton, Satinder P....
We present a noisy-OR Bayesian network model for simulation-based training, and an efficient search-based algorithm for automatic synthesis of plausible training scenarios from co...
Eugene Grois, William H. Hsu, Mikhail Voloshin, Da...
When dealing with signals from complex environments, where multiple time-dependent signal signatures can interfere with each other in stochastically unpredictable ways, traditiona...
Agents can benefit from contracting some of their tasks that cannot be performedby themselves or that can be performed moreefficiently by other agents. Developing an agent's ...
In the last decades enormous advances have been made possible for modelling complex (physical) systems by mathematical equations and computer algorithms. To deal with very long run...