Sciweavers

3643 search results - page 19 / 729
» Learning Submodular Functions
Sort
View
143
Voted
ICML
2007
IEEE
16 years 4 months ago
Tracking value function dynamics to improve reinforcement learning with piecewise linear function approximation
Reinforcement learning algorithms can become unstable when combined with linear function approximation. Algorithms that minimize the mean-square Bellman error are guaranteed to co...
Chee Wee Phua, Robert Fitch
ISMVL
1997
IEEE
134views Hardware» more  ISMVL 1997»
15 years 8 months ago
Functional Decomposition of MVL Functions Using Multi-Valued Decision Diagrams
In this paper, the minimization of incompletely specified multi-valued functions using functional decomposition is discussed. From the aspect of machine learning, learning sample...
Craig M. Files, Rolf Drechsler, Marek A. Perkowski
97
Voted
COLT
2004
Springer
15 years 9 months ago
Learning Monotonic Linear Functions
Adam Kalai
134
Voted
ICML
2009
IEEE
16 years 4 months ago
Kernelized value function approximation for reinforcement learning
Gavin Taylor, Ronald Parr
74
Voted
ICML
2008
IEEE
16 years 4 months ago
Actively learning level-sets of composite functions
Brent Bryan, Jeff G. Schneider