Learning Payoff Functions in Infinite Games
Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence. Pages 977-981.
Abstract
We consider a class of games with real-valued strategies and payoff information available only in the form of data from a given sample of strategy profiles. Solving such games with respect to the underlying strategy space requires generalizing from the data to a complete payoff-function representation. We address payoff-function learning as a standard regression problem, with provision for capturing known structure (symmetry) in the multiagent environment. To measure learning performance, we consider the relative utility of prescribed strategies, rather than the accuracy of payoff functions per se. We demonstrate our approach and evaluate its effectiveness on two examples: a two-player version of the first-price sealed-bid auction (with known analytical form), and a five-player marketbased scheduling game (with no known solution).
@inproceedings{ijcai2005p36,
title = {Learning Payoff Functions in Infinite Games},
author = {Vorobeychik, Yevgeniy and Wellman, Michael P. and Singh, Satinder},
booktitle = {Proceedings of the Nineteenth International Joint Conference on
Artificial Intelligence, {IJCAI-05}},
publisher = {International Joint Conferences on Artificial Intelligence},
pages = {977--981},
year = {2005},
url = {https://ijcai.org/proceedings/2005/36},
}
TY - CPAPER TI - Learning Payoff Functions in Infinite Games AU - Vorobeychik, Yevgeniy AU - Wellman, Michael P. AU - Singh, Satinder T2 - Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05 PB - International Joint Conferences on Artificial Intelligence PY - 2005 SP - 977 EP - 981 UR - https://ijcai.org/proceedings/2005/36 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
