Advice-exchange in heterogeneous groups of learning agents

Authors:
Luis Nunes;Eugénio Oliveira
Affiliations:
ISCTE/FEUP/LIACC-NIAD\'&R, ISCTE, Lisbon, Portugal;FEUP/LIACC-NIAD&R, FEUP, Porto, Portugal
Venue:
AAMAS '03 Proceedings of the second international joint conference on Autonomous agents and multiagent systems
Year:
2003

Citing 3
Cited 0

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Adaptation in natural and artificial systems

Adaptation in natural and artificial systems
Technical Note: \cal Q-Learning

Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

This research aims at studying the effects of exchanging information during the learning process in Multiagent Systems. The concept of advice-exchange, introduced in [3], consists in requesting extra feedback, in the form of episodic advice, from other agents that are solving similar problems. This work is concerned with the exchange of information in heterogeneous groups of learning-agents that either share the same environment or are solving problems with similar structure. Concepts, such as self confidence, trust and advisor preference, were introduced in the experiments that led to the results discussed in this paper.