Multiagent Reinforcement Learning with Adaptive State Focus
Reference
L. Buşoniu,
B. De Schutter, and
R. Babuška,
"Multiagent Reinforcement Learning with Adaptive State Focus," Proceedings of the 17th Belgium-Netherlands Conference on
Artificial Intelligence (BNAIC 2005) (K. Verbeeck, K. Tuyls, A.
Nowé, B. Manderick, and B. Kuijpers, eds.), Brussels, Belgium,
pp. 35-42, Oct. 2005.
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 deficiencies of learning on
the basis of a single agent's state.
Downloads
- Corresponding technical report:
pdf
file
(334 KB)
Bibtex entry
@inproceedings{BusDeS:05-017,
author={L. Bu{\c{s}}oniu and B. {D}e Schutter and R. Babu{\v{s}}ka},
title={Multiagent Reinforcement Learning with Adaptive State Focus},
booktitle={Proceedings of the 17th Belgium-Netherlands Conference on Artificial
Intelligence (BNAIC 2005)},
editor={K. Verbeeck and K. Tuyls and A. Now\'e and B. Manderick and B.
Kuijpers},
address={Brussels, Belgium},
pages={35--42},
month=oct,
year={2005}
}
This page is maintained by Bart De Schutter.
Last update: February 21, 2026.