Sciweavers

1895 search results - page 10 / 379
» Function learning from interpolation
Sort
View
ICML
2007
IEEE
14 years 8 months ago
Constructing basis functions from directed graphs for value function approximation
Basis functions derived from an undirected graph connecting nearby samples from a Markov decision process (MDP) have proven useful for approximating value functions. The success o...
Jeffrey Johns, Sridhar Mahadevan
ADCM
1999
49views more  ADCM 1999»
13 years 7 months ago
Dyadic Hermite interpolation on a rectangular mesh
: Given f and rf at the vertices of a rectangular mesh, we build an interpolating function f by a subdivision algorithm. The construction on each elementary rectangle is independen...
Serge Dubuc, Jean-Louis Merrien
PKDD
2010
Springer
179views Data Mining» more  PKDD 2010»
13 years 5 months ago
Gaussian Processes for Sample Efficient Reinforcement Learning with RMAX-Like Exploration
Abstract. We present an implementation of model-based online reinforcement learning (RL) for continuous domains with deterministic transitions that is specifically designed to achi...
Tobias Jung, Peter Stone
ICASSP
2011
IEEE
12 years 11 months ago
Causal signal recovery from U-invariant samples
Causal processing of a signal’s samples is crucial in on-line applications such as audio rate conversion, compression, tracking and more. This paper addresses the problem of cau...
Tomer Michaeli, Yonina C. Eldar, Volker Pohl
POPL
2012
ACM
12 years 3 months ago
Playing in the grey area of proofs
Interpolation is an important technique in verification and static analysis of programs. In particular, interpolants extracted from proofs of various properties are used in invar...
Krystof Hoder, Laura Kovács, Andrei Voronko...