Sciweavers

14 search results - page 2 / 3
» On the Convergence of Reduction-based and Model-based Method...
Sort
View
ICML
1995
IEEE
14 years 6 months ago
Stable Function Approximation in Dynamic Programming
The success ofreinforcement learninginpractical problems depends on the ability to combine function approximation with temporal di erence methods such as value iteration. Experime...
Geoffrey J. Gordon
IMAMS
2007
245views Mathematics» more  IMAMS 2007»
13 years 6 months ago
Discrete Surface Ricci Flow: Theory and Applications
Conformal geometry is in the core of pure mathematics. Conformal structure is more flexible than Riemaniann metric but more rigid than topology. Conformal geometric methods have p...
Miao Jin, Junho Kim, Xianfeng David Gu
CSFW
2010
IEEE
13 years 9 months ago
Impossibility Results for Secret Establishment
—Security protocol design is a creative discipline where the solution space depends on the problem to be solved and the cryptographic operators available. In this paper, we exami...
Benedikt Schmidt, Patrick Schaller, David A. Basin
KDD
2008
ACM
120views Data Mining» more  KDD 2008»
14 years 5 months ago
Multi-class cost-sensitive boosting with p-norm loss functions
We propose a family of novel cost-sensitive boosting methods for multi-class classification by applying the theory of gradient boosting to p-norm based cost functionals. We establ...
Aurelie C. Lozano, Naoki Abe
IROS
2008
IEEE
125views Robotics» more  IROS 2008»
13 years 11 months ago
Dynamic correlation matrix based multi-Q learning for a multi-robot system
—Multi-robot reinforcement learning is a very challenging area due to several issues, such as large state spaces, difficulty in reward assignment, nondeterministic action selecti...
Hongliang Guo, Yan Meng