Learning against opponents with bounded memory
Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence. Pages 817-821.
Abstract
Recently, a number of authors have proposed criteria for evaluating learning algorithms in multiagent systems. While well-justified, each of these has generally given little attention to one of the main challenges of a multi-agent setting: the capability of the other agents to adapt and learn as well. We propose extending existing criteria to apply to a class of adaptive opponents with bounded memory. We then show an algorithm that provably achieves an ǫ-best response against this richer class of opponents while simultaneously guaranteeing a minimum payoff against any opponent and performing well in self-play. This new algorithm also demonstrates strong performance in empirical tests against a variety of opponents in a wide range of environments.
@inproceedings{ijcai2005p167,
title = {Learning against opponents with bounded memory},
author = {Powers, Rob and Shoham, Yoav},
booktitle = {Proceedings of the Nineteenth International Joint Conference on
Artificial Intelligence, {IJCAI-05}},
publisher = {International Joint Conferences on Artificial Intelligence},
pages = {817--821},
year = {2005},
url = {https://ijcai.org/proceedings/2005/167},
}
TY - CPAPER TI - Learning against opponents with bounded memory AU - Powers, Rob AU - Shoham, Yoav T2 - Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05 PB - International Joint Conferences on Artificial Intelligence PY - 2005 SP - 817 EP - 821 UR - https://ijcai.org/proceedings/2005/167 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
