On stochastic imitation dynamics in large-scale networks
(2018) 16th European Control Conference, ECC 2018 p.2176-2181- Abstract
We consider a broad class of stochastic imitation dynamics over networks, encompassing several well known learning models such as the replicator dynamics. In the considered models, players have no global information about the game structure: they only know their own current utility and the one of neighbor players contacted through pairwise interactions in a network. In response to this information, players update their state according to some stochastic rules. For potential population games and complete interaction networks, we prove convergence and long-lasting permanence close to the evolutionary stable strategies of the game. These results refine and extend the ones known for deterministic imitation dynamics as they account for new... (More)
We consider a broad class of stochastic imitation dynamics over networks, encompassing several well known learning models such as the replicator dynamics. In the considered models, players have no global information about the game structure: they only know their own current utility and the one of neighbor players contacted through pairwise interactions in a network. In response to this information, players update their state according to some stochastic rules. For potential population games and complete interaction networks, we prove convergence and long-lasting permanence close to the evolutionary stable strategies of the game. These results refine and extend the ones known for deterministic imitation dynamics as they account for new emerging behaviors including meta-stability of the equilibria. Finally, we discuss extensions of our results beyond the fully mixed case, studying imitation dynamics where agents interact on complex communication networks.
(Less)
- author
- Zino, Lorenzo ; Como, Giacomo LU and Fagnani, Fabio
- organization
- publishing date
- 2018-11-27
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- 2018 European Control Conference, ECC 2018
- article number
- 8550419
- pages
- 6 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 16th European Control Conference, ECC 2018
- conference location
- Limassol, Cyprus
- conference dates
- 2018-06-12 - 2018-06-15
- external identifiers
-
- scopus:85059803151
- ISBN
- 9783952426982
- DOI
- 10.23919/ECC.2018.8550419
- language
- English
- LU publication?
- yes
- id
- 5ad3dd78-2fb1-477d-b54c-6a9e1678533e
- date added to LUP
- 2019-06-29 14:20:53
- date last changed
- 2022-05-03 23:32:01
@inproceedings{5ad3dd78-2fb1-477d-b54c-6a9e1678533e,
abstract = {{<p>We consider a broad class of stochastic imitation dynamics over networks, encompassing several well known learning models such as the replicator dynamics. In the considered models, players have no global information about the game structure: they only know their own current utility and the one of neighbor players contacted through pairwise interactions in a network. In response to this information, players update their state according to some stochastic rules. For potential population games and complete interaction networks, we prove convergence and long-lasting permanence close to the evolutionary stable strategies of the game. These results refine and extend the ones known for deterministic imitation dynamics as they account for new emerging behaviors including meta-stability of the equilibria. Finally, we discuss extensions of our results beyond the fully mixed case, studying imitation dynamics where agents interact on complex communication networks.</p>}},
author = {{Zino, Lorenzo and Como, Giacomo and Fagnani, Fabio}},
booktitle = {{2018 European Control Conference, ECC 2018}},
isbn = {{9783952426982}},
language = {{eng}},
month = {{11}},
pages = {{2176--2181}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
title = {{On stochastic imitation dynamics in large-scale networks}},
url = {{http://dx.doi.org/10.23919/ECC.2018.8550419}},
doi = {{10.23919/ECC.2018.8550419}},
year = {{2018}},
}