Partially observable Markov decision processes (POMDPs) are an intuitive and general way to model sequential decision making problems under uncertainty. Unfortunately, even approx...
Tao Wang, Pascal Poupart, Michael H. Bowling, Dale...
Robust model fitting is important for computer vision tasks due to the occurrence of multiple model instances, and, unknown nature of noise. The linear errors-in-variables (EIV) m...
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....
HDPS is a practical system for designing modeling paradigms, creating hierarchal model definitions, and evaluating multi-paradigm models - particularly in business and finance. HD...
We present a connectionist architecture that supports almost instantaneous deductive and abductive reasoning. The deduction algorithm responds in few steps for single rule queries...