On the Outcome Equivalence of Extensive-Form and Behavioral Correlated Equilibria

Abstract

We investigate two notions of correlated equilibrium for extensive-form games: the extensive-form correlated equilibrium (EFCE) and the behavioral correlated equilibrium (BCE). We show that the two are outcome-equivalent, in the sense that every outcome distribution achievable under one notion is achievable under the other. Our result implies, to our knowledge, the first polynomial-time algorithm for computing a BCE.

Cite

Text

Zhang and Sandholm. "On the Outcome Equivalence of Extensive-Form and Behavioral Correlated Equilibria." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I9.28859

Markdown

[Zhang and Sandholm. "On the Outcome Equivalence of Extensive-Form and Behavioral Correlated Equilibria." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/zhang2024aaai-outcome/) doi:10.1609/AAAI.V38I9.28859

BibTeX

@inproceedings{zhang2024aaai-outcome,
  title     = {{On the Outcome Equivalence of Extensive-Form and Behavioral Correlated Equilibria}},
  author    = {Zhang, Brian Hu and Sandholm, Tuomas},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {9969-9976},
  doi       = {10.1609/AAAI.V38I9.28859},
  url       = {https://mlanthology.org/aaai/2024/zhang2024aaai-outcome/}
}