Sciweavers

74 search results - page 5 / 15
» Formalizing Multi-state Learning Dynamics
Sort
View
ATAL
2007
Springer
14 years 4 months ago
Theoretical advantages of lenient Q-learners: an evolutionary game theoretic perspective
This paper presents the dynamics of multiple reinforcement learning agents from an Evolutionary Game Theoretic (EGT) perspective. We provide a Replicator Dynamics model for tradit...
Liviu Panait, Karl Tuyls
ISOLA
2010
Springer
13 years 8 months ago
LivingKnowledge: Kernel Methods for Relational Learning and Semantic Modeling
Latest results of statistical learning theory have provided techniques such us pattern analysis and relational learning, which help in modeling system behavior, e.g. the semantics ...
Alessandro Moschitti
IJCNN
2006
IEEE
14 years 4 months ago
A Structured Context Model for Grammar Learning
—We present a structured model of context that supports an integrated approach to language acquisition and use. The model extends an existing formal notation, Embodied Constructi...
Nancy Chang, Eva Mok
AAAI
1996
13 years 11 months ago
Learning to Take Actions
We formalize a model for supervised learning of action strategies in dynamic stochastic domains and show that PAC-learning results on Occam algorithms hold in this model as well. W...
Roni Khardon
JAIR
2002
120views more  JAIR 2002»
13 years 10 months ago
Learning Geometrically-Constrained Hidden Markov Models for Robot Navigation: Bridging the Topological-Geometrical Gap
Hidden Markov models hmms and partially observable Markov decision processes pomdps provide useful tools for modeling dynamical systems. They are particularly useful for represent...
Hagit Shatkay, Leslie Pack Kaelbling