D-CIS Publication Database

Publication

Type of publication:Inproceedings
Entered by:LB
TitleMultiagent Reinforcement Learning with Adaptive State Focus
Bibtex cite IDBusoniu-bnaic05
Booktitle Proceedings of the 17th Belgian-Dutch Conference on Artificial Intelligence (BNAIC 2005)
Year published 2005
Month October
Pages 35-42
Location 17-18 October 2005, Brussels, Belgium
Keywords multiagent learning,reinforcement learning,Q-learning,coordination
Abstract
In realistic multiagent systems, learning on the basis of complete state information is not feasible. We introduce adaptive state focus Q-learning, a class of methods derived from Q-learning that start learning with only the state information that is strictly necessary for a single agent to perform the task, and that monitor the convergence of learning. If lack of convergence is detected, the learner dynamically expands its state space to incorporate more state information (e.g., states of other agents). Learning is faster and takes less resources than if the complete state were considered from the start, while being able to handle situations where agents interfere in pursuing their goals. We illustrate our approach by instantiating a simple version of such a method, and by showing that it outperforms learning with full state information without being hindered by the de ciencies of learning on the basis of a single agent's state.
Authors
Busoniu, Lucian
De Schutter, Bart
Babuška, Robert
Topics
=SEE CLASSIFICATION DIFFERENCE FROM OTHERS=
BibTeXBibTeX
RISRIS
Attachments
 
Total mark: 5