Sciweavers

589 search results - page 12 / 118
» Learning to Transfer Knowledge between Reference Systems
Sort
View
ATAL
2008
Springer
14 years 11 months ago
Autonomous transfer for reinforcement learning
Recent work in transfer learning has succeeded in making reinforcement learning algorithms more efficient by incorporating knowledge from previous tasks. However, such methods typ...
Matthew E. Taylor, Gregory Kuhlmann, Peter Stone
ECTEL
2009
Springer
15 years 1 months ago
Context-Aware Combination of Adapted User Profiles for Interchange of Knowledge between Peers
Abstract. This paper presents a system that connects students with complementary profiles, so they can interchange knowledge and help each other. The profile of the students is bui...
Sergio Gutiérrez Santos, Mario Muñoz...
AAAI
2006
14 years 10 months ago
Using Homomorphisms to Transfer Options across Continuous Reinforcement Learning Domains
We examine the problem of Transfer in Reinforcement Learning and present a method to utilize knowledge acquired in one Markov Decision Process (MDP) to bootstrap learning in a mor...
Vishal Soni, Satinder P. Singh
AUTOMATICA
2008
108views more  AUTOMATICA 2008»
14 years 9 months ago
Closed-loop identification of multivariable systems: With or without excitation of all references?
The accuracy of plant parameters estimated in closed-loop operation is investigated for a class of multivariable systems and for the situation where only some of the reference inp...
Ljubisa Miskovic, Alireza Karimi, Dominique Bonvin...
ECTEL
2007
Springer
15 years 3 months ago
Service-oriented Knowledge Architectures - Integrating Learning and Business Information Systems
This paper presents a dissertation project on business-integrated, service-oriented learning architectures. The isolation of corporate learning management from core business functi...
Katrina Leyking