Approximate nash equilibria in partially observed stochastic games with mean-field interactions

Name: Approximate nash equilibria in partially observed stochastic games with mean-field interactions
Author: Saldı, Naci, Başar, T., Raginsky, M.

İsim	Approximate nash equilibria in partially observed stochastic games with mean-field interactions
Yazar	Saldı, Naci, Başar, T., Raginsky, M.
Basım Tarihi:	2019-08
Basım Yeri	- Informs
Konu	Mean-field games, Approximate Nash equilibrium, Partially observed stochastic control
Tür	Süreli Yayın
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	0364-765X
Kayıt Numarası	38d9b62d-e973-4a7f-b6a5-df6d77264d70
Lokasyon	Natural and Mathematical Sciences
Tarih	2019-08
Notlar	U.S. Air Force Office of Scientific Research through the Multidisciplinary University Research Initiative (MURI) ; MURI Office of Naval Research
Örnek Metin	Establishing the existence of Nash equilibria for partially observed stochastic dynamic games is known to be quite challenging, with the difficulties stemming from the noisy nature of the measurements available to individual players (agents) and the decentralized nature of this information. When the number of players is sufficiently large and the interactions among agents is of the mean-field type, one way to overcome this challenge is to investigate the infinite-population limit of the problem, which leads to a mean-field game. In this paper, we consider discrete-time partially observed mean-field games with infinite-horizon discounted-cost criteria. Using the technique of converting the original partially observed stochastic control problem to a fully observed one on the belief space and the dynamic programming principle, we establish the existence of Nash equilibria for these game models under very mild technical conditions. Then, we show that the mean-field equilibrium policy, when adopted by each agent, forms an approximate Nash equilibrium for games with sufficiently many agents.
DOI	10.1287/moor.2018.0957
Cilt	44

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Approximate nash equilibria in partially observed stochastic games with mean-field interactions

Yazar Saldı, Naci, Başar, T., Raginsky, M.

Basım Tarihi 2019-08

Basım Yeri - Informs

Konu Mean-field games, Approximate Nash equilibrium, Partially observed stochastic control

Tür Süreli Yayın

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 0364-765X

Kayıt Numarası 38d9b62d-e973-4a7f-b6a5-df6d77264d70

Lokasyon Natural and Mathematical Sciences

Tarih 2019-08

Notlar U.S. Air Force Office of Scientific Research through the Multidisciplinary University Research Initiative (MURI) ; MURI Office of Naval Research

Örnek Metin Establishing the existence of Nash equilibria for partially observed stochastic dynamic games is known to be quite challenging, with the difficulties stemming from the noisy nature of the measurements available to individual players (agents) and the decentralized nature of this information. When the number of players is sufficiently large and the interactions among agents is of the mean-field type, one way to overcome this challenge is to investigate the infinite-population limit of the problem, which leads to a mean-field game. In this paper, we consider discrete-time partially observed mean-field games with infinite-horizon discounted-cost criteria. Using the technique of converting the original partially observed stochastic control problem to a fully observed one on the belief space and the dynamic programming principle, we establish the existence of Nash equilibria for these game models under very mild technical conditions. Then, we show that the mean-field equilibrium policy, when adopted by each agent, forms an approximate Nash equilibrium for games with sufficiently many agents.

DOI 10.1287/moor.2018.0957

Cilt 44