ML Anthology

Friend-or-Foe Q-Learning in General-Sum Games

Michael L. Littman
ICML 2001 pp. 322-328
/icml/2001/littman2001icml-friend/

Abstract

This paper describes an approach to rein-forcement learning in multiagent general-sum games in which a learner is told to treat each other agent as either a \\friend " or \\foe". This Q-learning-style algorithm provides strong convergence guarantees compared to an ex-isting Nash-equilibrium-based learning rule.

Semantic Scholar

Cite

Text

Littman. "Friend-or-Foe Q-Learning in General-Sum Games." International Conference on Machine Learning, 2001.

Markdown

[Littman. "Friend-or-Foe Q-Learning in General-Sum Games." International Conference on Machine Learning, 2001.](https://mlanthology.org/icml/2001/littman2001icml-friend/)

BibTeX

@inproceedings{littman2001icml-friend,
  title     = {{Friend-or-Foe Q-Learning in General-Sum Games}},
  author    = {Littman, Michael L.},
  booktitle = {International Conference on Machine Learning},
  year      = {2001},
  pages     = {322-328},
  url       = {https://mlanthology.org/icml/2001/littman2001icml-friend/}
}