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
BibTeX
@inproceedings{BusDeS:05-017,
author = {Bu{\c{s}}oniu, Lucian and De Schutter, Bart and Babu{\v{s}}ka,
Robert},
title = {Multiagent Reinforcement Learning with Adaptive State Focus},
booktitle = {Proceedings of the 17th Belgium-Netherlands Conference on
Artificial Intelligence (BNAIC 2005)},
editor = {Verbeeck, Katja and Tuyls, Karl and Now\'{e}, Ann and
Manderick, Bernard and Kuijpers, Bart},
address = {Brussels, Belgium},
pages = {35--42},
month = oct,
year = {2005}
}