Abstract— Almost all learning machines used in computational intelligence are not regular but singular statistical models, because they are nonidentifiable and their Fisher info...
Standard Reinforcement Learning (RL) aims to optimize decision-making rules in terms of the expected return. However, especially for risk-management purposes, other criteria such ...
In categorial systems with a fixed structural component, the learning problem comes down to finding the solution for a set of typeassignment equations. A hard-wired structural co...
We derive a family of kernels on dynamical systems by applying the Binet-Cauchy theorem to trajectories of states. Our derivation provides a unifying framework for all kernels on d...
S. V. N. Vishwanathan, Alexander J. Smola, Ren&eac...
Policy evaluation is a critical step in the approximate solution of large Markov decision processes (MDPs), typically requiring O(|S|3 ) to directly solve the Bellman system of |S...