We derive categories directly from robot sensor data to address the symbol grounding problem. Unlike model-based approaches where human intuitive correspondences are sought betwee...
Daniel H. Grollman, Odest Chadwicke Jenkins, Frank...
— We present a near-optimal deterministic filter for systems that evolve on the unit circle. Unlike suboptimal filtering algorithms that rely on approximations of the system, t...
Paul William Coote, Jochen Trumpf, Robert E. Mahon...
Abstract. Switching linear dynamic systems (SLDS) attempt to describe a complex nonlinear dynamic system with a succession of linear models indexed by a switching variable. Unfortu...
s of Invited Presentations The Mathematics of Matter and the Mathematics of Mind . . . . . . . . . . . . . 1 David Berlinski A Grand Challenge: Full Reactive Modeling of a Multi-ce...
Dynamic Programming, Q-learning and other discrete Markov Decision Process solvers can be applied to continuous d-dimensional state-spaces by quantizing the state space into an arr...