89 search results - page 4 / 18 » Stable Function Approximation in Dynamic Programming |
155
click to vote
JCP
2007
15 years 3 months ago
2007
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...
122
click to vote
ESANN
2006
15 years 5 months ago
2006
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...
141
click to vote
ATAL
2010
Springer
14 years 10 months ago
2010
Springer
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...
133
click to vote
ICCS
2007
Springer
15 years 10 months ago
2007
Springer
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 ...
117
click to vote
NIPS
2000
15 years 5 months ago
2000
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...