Coordinating partially-informed agents over state-dependent networks

Benjamin Larrousse; Samson Lasaulce; Michèle Wigger

doi:10.1109/ITW.2015.7133152

Coordinating partially-informed agents over state-dependent networks

Benjamin Larrousse
, Samson Lasaulce
, Michèle Wigger

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We consider a multi-agent scenario with K ≥ 2 agents that have partial information about some random nature state, and that take actions in a repeated manner. Each agent also has imperfect observations of the other agents' past actions and the nature state realization. Our goal is to characterize the set of asymptotically implementable distributions on the agents' actions and the nature state. We solve this problem for general K when all agents have only causal nature state information (NSI) and for K = 2 when: one agent has causal NSI and the other agent has non-causal NSI; or in some special cases when both agents have non-causal NSI.

Original language	English
Title of host publication	2015 IEEE Information Theory Workshop, ITW 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781479955268
DOIs	https://doi.org/10.1109/ITW.2015.7133152
Publication status	Published - 24 Jun 2015
Event	2015 IEEE Information Theory Workshop, ITW 2015 - Jerusalem, Israel Duration: 26 Apr 2015 → 1 May 2015

Publication series

Name	2015 IEEE Information Theory Workshop, ITW 2015

Conference

Conference	2015 IEEE Information Theory Workshop, ITW 2015
Country/Territory	Israel
City	Jerusalem
Period	26/04/15 → 1/05/15

Access to Document

10.1109/ITW.2015.7133152

Cite this

@inproceedings{e46a868d15c846cc95c109fc9daa915b,

title = "Coordinating partially-informed agents over state-dependent networks",

abstract = "We consider a multi-agent scenario with K ≥ 2 agents that have partial information about some random nature state, and that take actions in a repeated manner. Each agent also has imperfect observations of the other agents' past actions and the nature state realization. Our goal is to characterize the set of asymptotically implementable distributions on the agents' actions and the nature state. We solve this problem for general K when all agents have only causal nature state information (NSI) and for K = 2 when: one agent has causal NSI and the other agent has non-causal NSI; or in some special cases when both agents have non-causal NSI.",

author = "Benjamin Larrousse and Samson Lasaulce and Mich{\`e}le Wigger",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 2015 IEEE Information Theory Workshop, ITW 2015 ; Conference date: 26-04-2015 Through 01-05-2015",

year = "2015",

month = jun,

day = "24",

doi = "10.1109/ITW.2015.7133152",

language = "English",

series = "2015 IEEE Information Theory Workshop, ITW 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2015 IEEE Information Theory Workshop, ITW 2015",

}

Larrousse, B, Lasaulce, S & Wigger, M 2015, Coordinating partially-informed agents over state-dependent networks. in 2015 IEEE Information Theory Workshop, ITW 2015., 7133152, 2015 IEEE Information Theory Workshop, ITW 2015, Institute of Electrical and Electronics Engineers Inc., 2015 IEEE Information Theory Workshop, ITW 2015, Jerusalem, Israel, 26/04/15. https://doi.org/10.1109/ITW.2015.7133152

Coordinating partially-informed agents over state-dependent networks. / Larrousse, Benjamin; Lasaulce, Samson; Wigger, Michèle.
2015 IEEE Information Theory Workshop, ITW 2015. Institute of Electrical and Electronics Engineers Inc., 2015. 7133152 (2015 IEEE Information Theory Workshop, ITW 2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Coordinating partially-informed agents over state-dependent networks

AU - Larrousse, Benjamin

AU - Lasaulce, Samson

AU - Wigger, Michèle

PY - 2015/6/24

Y1 - 2015/6/24

N2 - We consider a multi-agent scenario with K ≥ 2 agents that have partial information about some random nature state, and that take actions in a repeated manner. Each agent also has imperfect observations of the other agents' past actions and the nature state realization. Our goal is to characterize the set of asymptotically implementable distributions on the agents' actions and the nature state. We solve this problem for general K when all agents have only causal nature state information (NSI) and for K = 2 when: one agent has causal NSI and the other agent has non-causal NSI; or in some special cases when both agents have non-causal NSI.

AB - We consider a multi-agent scenario with K ≥ 2 agents that have partial information about some random nature state, and that take actions in a repeated manner. Each agent also has imperfect observations of the other agents' past actions and the nature state realization. Our goal is to characterize the set of asymptotically implementable distributions on the agents' actions and the nature state. We solve this problem for general K when all agents have only causal nature state information (NSI) and for K = 2 when: one agent has causal NSI and the other agent has non-causal NSI; or in some special cases when both agents have non-causal NSI.

U2 - 10.1109/ITW.2015.7133152

DO - 10.1109/ITW.2015.7133152

M3 - Conference contribution

AN - SCOPUS:84938943657

T3 - 2015 IEEE Information Theory Workshop, ITW 2015

BT - 2015 IEEE Information Theory Workshop, ITW 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2015 IEEE Information Theory Workshop, ITW 2015

Y2 - 26 April 2015 through 1 May 2015

ER -

Coordinating partially-informed agents over state-dependent networks

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this