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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [16 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01272502
Contributor : Samson Lasaulce <>
Submitted on : Monday, February 15, 2016 - 11:20:55 AM
Last modification on : Thursday, April 11, 2019 - 2:30:07 PM
Document(s) archivé(s) le : Saturday, November 12, 2016 - 5:06:13 PM

File

ITW-2015-Larrousse-etal-5.pdf
Files produced by the author(s)

Identifiers

Citation

Benjamin Larrousse, Samson Lasaulce, Michèle Wigger. Coordinating partially-informed agents over state-dependent networks. 2015 IEEE Information Theory Workshop (ITW), Apr 2015, Jérusalem, Israel. ⟨10.1109/ITW.2015.7133152⟩. ⟨hal-01272502⟩

Share

Metrics

Record views

265

Files downloads

108