Sciweavers

13376 search results - page 473 / 2676
» Problem Solving with
Sort
View
168
Voted
ATAL
2004
Springer
15 years 11 months ago
Time-Extended Policies in Multi-Agent Reinforcement Learning
Many algorithms such as Q-learning successfully address reinforcement learning in single-agent multi-time-step problems. In addition there are methods that address reinforcement l...
Kagan Tumer, Adrian K. Agogino
161
Voted
EXPCS
2007
15 years 10 months ago
Performance testing of combinatorial solvers with isomorph class instances
Combinatorial optimization problems expressed as Boolean constraint satisfaction problems (BCSPs) arise in several contexts, ranging from the classical unate set-packing problems ...
Franc Brglez, Jason A. Osborne
259
Voted
PAMI
2011
15 years 1 months ago
Dynamic Programming and Graph Algorithms in Computer Vision
Optimization is a powerful paradigm for expressing and solving problems in a wide range of areas, and has been successfully applied to many vision problems. Discrete optimization ...
Pedro F. Felzenszwalb, Ramin Zabih
152
Voted
NCA
2005
IEEE
15 years 11 months ago
Protocol Composition Frameworks A Header-Driven Model
Protocol composition frameworks provide off-the-shelf composable protocols to simplify the development of custom protocol stacks. All recent protocol frameworks use a general-purp...
Daniel C. Bünzli, Sergio Mena, Uwe Nestmann
ECML
2007
Springer
16 years 9 days ago
Fast Optimization Methods for L1 Regularization: A Comparative Study and Two New Approaches
L1 regularization is effective for feature selection, but the resulting optimization is challenging due to the non-differentiability of the 1-norm. In this paper we compare state...
Mark Schmidt, Glenn Fung, Rómer Rosales