Sciweavers

495 search results - page 12 / 99
» Approximation algorithms for budgeted learning problems
Sort
View
ECML
2004
Springer
14 years 1 months ago
Model Approximation for HEXQ Hierarchical Reinforcement Learning
HEXQ is a reinforcement learning algorithm that discovers hierarchical structure automatically. The generated task hierarchy repthe problem at different levels of abstraction. In ...
Bernhard Hengst
ACCV
2009
Springer
14 years 3 months ago
An Online Framework for Learning Novel Concepts over Multiple Cues
Abstract. We propose an online learning algorithm to tackle the problem of learning under limited computational resources in a teacher-student scenario, over multiple visual cues. ...
Luo Jie, Francesco Orabona, Barbara Caputo
ICRA
2008
IEEE
113views Robotics» more  ICRA 2008»
14 years 2 months ago
Reinforcement learning with function approximation for cooperative navigation tasks
— In this paper, we propose a reinforcement learning approach to address multi-robot cooperative navigation tasks in infinite settings. We propose an algorithm to simultaneously...
Francisco S. Melo, M. Isabel Ribeiro
FOCS
2008
IEEE
14 years 2 months ago
Submodular Approximation: Sampling-based Algorithms and Lower Bounds
We introduce several generalizations of classical computer science problems obtained by replacing simpler objective functions with general submodular functions. The new problems i...
Zoya Svitkina, Lisa Fleischer
SPLC
2008
13 years 10 months ago
Filtered Cartesian Flattening: An Approximation Technique for Optimally Selecting Features while Adhering to Resource Constraint
Software Product-lines (SPLs) use modular software components that can be reconfigured into different variants for different requirements sets. Feature modeling is a common method...
Jules White, B. Doughtery, Douglas C. Schmidt