Paper Info
Title
Mutual online concept learning for multiple agents
Abstract
To create multi-agent systems that are both adaptive and open, agents must collectively learn to generate and adapt their own concepts, ontologies, interpretations, and even languages actively in an online fashion. A central issue is the potential lack of any pre-existing concept to be learned; instead, agents may need to collectively design a concept that is evolving as they exchange information. This paper presents a framework for mutual online concept learning (MOCL) in a shared world. MOCL extends classical online concept learning from single-agent to multi-agent settings. Based on the Perceptron algorithm, we present a specific MOCL algorithm, called the mutual perceptron convergence algorithm, which can converge within a finite number of mistakes under some conditions. Analysis of the convergence conditions shows that the possibility of convergence depends on the quality of the instances they produce. Finally, we point out applications of MOCL and the convergence algorithm to the formation of adaptive ontological and linguistic knowledge such as dynamically generated shared vocabulary and grammar structures.
Year
DOI
Venue
2002
10.1145/544741.544830
AAMAS
Keywords
Field
DocType
online fashion,specific mocl algorithm,pre-existing concept,own concept,mutual perceptron convergence algorithm,perceptron algorithm,convergence condition,mutual online concept learning,convergence algorithm,multiple agent,classical online concept,multi agent system,concept learning
Convergence (routing),Ontology (information science),Ontology,Finite set,Computer science,Concept learning,Theoretical computer science,Grammar,Artificial intelligence,Perceptron,Vocabulary,Machine learning
Conference
ISBN
Citations 
PageRank 
1-58113-480-0
11
1.02
References 
Authors
10
2
Name
Order
Citations
PageRank
Jun Wang11099.52
Les Gasser21601261.00