ML Anthology

Learning Cooperative Games

Maria-Florina Balcan, Ariel D. Procaccia, Yair Zick
IJCAI 2015 pp. 475-481
/ijcai/2015/balcan2015ijcai-learning/

Abstract

This paper explores a PAC (probably approximately correct) learning model in cooperative games. Specifically, we are given m random samples of coalitions and their values, taken from some unknown cooperative game; can we predict the values of unseen coalitions? We study the PAC learnability of several well-known classes of cooperative games, such as network flow games, threshold task games, and induced subgraph games. We also establish a novel connection between PAC learnability and core stability: for games that are efficiently learnable, it is possible to find payoff divisions that are likely to be stable using a polynomial number of samples.

PDF IJCAI Semantic Scholar

Cite

Text

Balcan et al. "Learning Cooperative Games." International Joint Conference on Artificial Intelligence, 2015.

Markdown

[Balcan et al. "Learning Cooperative Games." International Joint Conference on Artificial Intelligence, 2015.](https://mlanthology.org/ijcai/2015/balcan2015ijcai-learning/)

BibTeX

@inproceedings{balcan2015ijcai-learning,
  title     = {{Learning Cooperative Games}},
  author    = {Balcan, Maria-Florina and Procaccia, Ariel D. and Zick, Yair},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2015},
  pages     = {475-481},
  url       = {https://mlanthology.org/ijcai/2015/balcan2015ijcai-learning/}
}