Learning to Play Efficient Coarse Correlated Equilibria

Holly P. Borowski; Jason R. Marden; Jeff S. Shamma

doi:10.1007/s13235-018-0244-z

Learning to Play Efficient Coarse Correlated Equilibria

Holly P. Borowski, Jason R. Marden, Jeff S. Shamma

Research output: Contribution to journal › Article › peer-review

8 Scopus citations

Abstract

The majority of the distributed learning literature focuses on convergence to Nash equilibria. Coarse correlated equilibria, on the other hand, can often characterize more efficient collective behavior than even the best Nash equilibrium. However, there are no existing distributed learning algorithms that converge to specific coarse correlated equilibria. In this paper, we provide one such algorithm, which guarantees that the agents’ collective joint strategy will constitute an efficient coarse correlated equilibrium with high probability. The key to attaining efficient correlated behavior through distributed learning involves incorporating a common random signal into the learning environment.

Original language	English (US)
Pages (from-to)	24-46
Number of pages	23
Journal	Dynamic Games and Applications
Volume	9
Issue number	1
DOIs	https://doi.org/10.1007/s13235-018-0244-z
State	Published - Mar 10 2018

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01
Acknowledgements: This research was supported by ONR grant #N00014-17-1-2060, NSF grant #ECCS-1638214, the NASA Aeronautics scholarship program, the Philanthropic Educational Organization, and the Zonta International Amelia Earhart fellowship program, and funding from King Abdullah University of Science and Technology (KAUST).

Access to Document

10.1007/s13235-018-0244-z

Cite this

@article{4b94891f0d89495a8974844b9a0903c7,

title = "Learning to Play Efficient Coarse Correlated Equilibria",

abstract = "The majority of the distributed learning literature focuses on convergence to Nash equilibria. Coarse correlated equilibria, on the other hand, can often characterize more efficient collective behavior than even the best Nash equilibrium. However, there are no existing distributed learning algorithms that converge to specific coarse correlated equilibria. In this paper, we provide one such algorithm, which guarantees that the agents{\textquoteright} collective joint strategy will constitute an efficient coarse correlated equilibrium with high probability. The key to attaining efficient correlated behavior through distributed learning involves incorporating a common random signal into the learning environment.",

author = "Borowski, {Holly P.} and Marden, {Jason R.} and Shamma, {Jeff S.}",

note = "KAUST Repository Item: Exported on 2020-10-01 Acknowledgements: This research was supported by ONR grant #N00014-17-1-2060, NSF grant #ECCS-1638214, the NASA Aeronautics scholarship program, the Philanthropic Educational Organization, and the Zonta International Amelia Earhart fellowship program, and funding from King Abdullah University of Science and Technology (KAUST).",

year = "2018",

month = mar,

day = "10",

doi = "10.1007/s13235-018-0244-z",

language = "English (US)",

volume = "9",

pages = "24--46",

journal = "Dynamic Games and Applications",

issn = "2153-0785",

publisher = "Springer Science + Business Media",

number = "1",

}

TY - JOUR

T1 - Learning to Play Efficient Coarse Correlated Equilibria

AU - Borowski, Holly P.

AU - Marden, Jason R.

AU - Shamma, Jeff S.

N1 - KAUST Repository Item: Exported on 2020-10-01 Acknowledgements: This research was supported by ONR grant #N00014-17-1-2060, NSF grant #ECCS-1638214, the NASA Aeronautics scholarship program, the Philanthropic Educational Organization, and the Zonta International Amelia Earhart fellowship program, and funding from King Abdullah University of Science and Technology (KAUST).

PY - 2018/3/10

Y1 - 2018/3/10

N2 - The majority of the distributed learning literature focuses on convergence to Nash equilibria. Coarse correlated equilibria, on the other hand, can often characterize more efficient collective behavior than even the best Nash equilibrium. However, there are no existing distributed learning algorithms that converge to specific coarse correlated equilibria. In this paper, we provide one such algorithm, which guarantees that the agents’ collective joint strategy will constitute an efficient coarse correlated equilibrium with high probability. The key to attaining efficient correlated behavior through distributed learning involves incorporating a common random signal into the learning environment.

AB - The majority of the distributed learning literature focuses on convergence to Nash equilibria. Coarse correlated equilibria, on the other hand, can often characterize more efficient collective behavior than even the best Nash equilibrium. However, there are no existing distributed learning algorithms that converge to specific coarse correlated equilibria. In this paper, we provide one such algorithm, which guarantees that the agents’ collective joint strategy will constitute an efficient coarse correlated equilibrium with high probability. The key to attaining efficient correlated behavior through distributed learning involves incorporating a common random signal into the learning environment.

UR - http://hdl.handle.net/10754/627456

UR - https://link.springer.com/article/10.1007%2Fs13235-018-0244-z

UR - http://www.scopus.com/inward/record.url?scp=85061779765&partnerID=8YFLogxK

U2 - 10.1007/s13235-018-0244-z

DO - 10.1007/s13235-018-0244-z

M3 - Article

SN - 2153-0785

VL - 9

SP - 24

EP - 46

JO - Dynamic Games and Applications

JF - Dynamic Games and Applications

IS - 1

ER -

Learning to Play Efficient Coarse Correlated Equilibria

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this