Correlated Q-Learning

Amy Greenwald, Keith HallICML 2003 · OpenReview

Abstract

This paper introduces Correlated-Q (CE-Q) learning, a multiagent Q-learning algorithm based on the correlated equilibrium (CE) solution concept. CE-Q generalizes both Nash-Q and Friend-and-Foe-Q: in general-sum games, the set of correlated equilibria contains the set of Nash equilibria; in constant-sum games, the set of correlated equilibria contains the set of minimax equilibria. This paper describes experiments with four variants of CE-Q, demonstrating empirical convergence to equilibrium policies on a testbed of general-sum Markov games.
BibTeX
@inproceedings{greenwald2003correlated,
  author = {Amy Greenwald and Keith Hall},
  title = {{Correlated Q-Learning}},
  booktitle = {International Conference on Machine Learning},
  year = {2003},
  url = {https://openreview.net/forum?id=rk-majbuZS},
}

Loading related content...

Figure