Abstract— We describe a general method to transform a non-Markovian sequential decision problem into a supervised learning problem using a K-bestpaths algorithm. We consider an a...
We focus on neuro-dynamic programming methods to learn state-action value functions and outline some of the inherent problems to be faced, when performing reinforcement learning in...
The Affine ADD (AADD) is an extension of the Algebraic Decision Diagram (ADD) that compactly represents context-specific, additive and multiplicative structure in functions from a...
Scott Sanner, William T. B. Uther, Karina Valdivia...
Abstract. We extend the hyperdynamics method developed for lowdimensional energy-dominated systems, to simulate slow dynamics in more general atomistic systems. We show that a few ...
We propose a method of approximate dynamic programming for Markov decision processes (MDPs) using algebraic decision diagrams (ADDs). We produce near-optimal value functions and p...