Sciweavers

140 search results - page 10 / 28
» Structural Abstraction Experiments in Reinforcement Learning
Sort
View
ICMLA
2010
15 years 1 months ago
Robust Learning for Adaptive Programs by Leveraging Program Structure
Abstract--We study how to effectively integrate reinforcement learning (RL) and programming languages via adaptation-based programming, where programs can include non-deterministic...
Jervis Pinto, Alan Fern, Tim Bauer, Martin Erwig
TMM
2010
199views Management» more  TMM 2010»
14 years 10 months ago
Video Annotation Through Search and Graph Reinforcement Mining
Abstract--Unlimited vocabulary annotation of multimedia documents remains elusive despite progress solving the problem in the case of a small, fixed lexicon. Taking advantage of th...
Emily Moxley, Tao Mei, Bangalore S. Manjunath
CEC
2008
IEEE
15 years 6 months ago
Learning benefits evolution if sex gives pleasure
Abstract-- In this paper we investigate the effects of individual learning on an evolving population of situated agents. We work with a novel type of system where agents can decide...
Robert Griffioen, Selmar K. Smit, A. E. Eiben
IJCNN
2007
IEEE
15 years 10 months ago
Adaptive Dynamic Modularity in a Connectionist Model of Context-Dependent Idea Generation
Abstract— Cognitive control - the ability to produce appropriate behavior in complex situations - is a fundamental aspect of intelligence. It is increasingly evident that this co...
Simona Doboli, Ali A. Minai, Vincent R. Brown
IROS
2006
IEEE
107views Robotics» more  IROS 2006»
15 years 10 months ago
Heterogeneous and Hierarchical Cooperative Learning via Combining Decision Trees
Abstract— Decision trees, being human readable and hierarchically structured, provide a suitable mean to derive state-space abstraction and simplify the inclusion of the availabl...
Masoud Asadpour, Majid Nili Ahmadabadi, Roland Sie...