Q-learning in regularized mean-field games

Name: Q-learning in regularized mean-field games
Author: Anahtarcı, Berkay, Karıksız, Can Deha, Saldı, N.

İsim	Q-learning in regularized mean-field games
Yazar	Anahtarcı, Berkay, Karıksız, Can Deha, Saldı, N.
Basım Tarihi:	2023-03
Basım Yeri	- Springer
Konu	Discounted reward, Mean-field games, Q-learning, Regularized Markov decision processes
Tür	Süreli Yayın
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	2153-0785
Kayıt Numarası	60eb43e0-5e18-444f-9a58-62e50c99b500
Lokasyon	Natural and Mathematical Sciences
Tarih	2023-03
Notlar	BAGEP Award of the Science Academy
Örnek Metin	In this paper, we introduce a regularized mean-field game and study learning of this game under an infinite-horizon discounted reward function. Regularization is introduced by adding a strongly concave regularization function to the one-stage reward function in the classical mean-field game model. We establish a value iteration based learning algorithm to this regularized mean-field game using fitted Q-learning. The regularization term in general makes reinforcement learning algorithm more robust to the system components. Moreover, it enables us to establish error analysis of the learning algorithm without imposing restrictive convexity assumptions on the system components, which are needed in the absence of a regularization term.
DOI	10.1007/s13235-022-00450-2
Cilt	13

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Q-learning in regularized mean-field games

Yazar Anahtarcı, Berkay, Karıksız, Can Deha, Saldı, N.

Basım Tarihi 2023-03

Basım Yeri - Springer

Konu Discounted reward, Mean-field games, Q-learning, Regularized Markov decision processes

Tür Süreli Yayın

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 2153-0785

Kayıt Numarası 60eb43e0-5e18-444f-9a58-62e50c99b500

Lokasyon Natural and Mathematical Sciences

Tarih 2023-03

Notlar BAGEP Award of the Science Academy

Örnek Metin In this paper, we introduce a regularized mean-field game and study learning of this game under an infinite-horizon discounted reward function. Regularization is introduced by adding a strongly concave regularization function to the one-stage reward function in the classical mean-field game model. We establish a value iteration based learning algorithm to this regularized mean-field game using fitted Q-learning. The regularization term in general makes reinforcement learning algorithm more robust to the system components. Moreover, it enables us to establish error analysis of the learning algorithm without imposing restrictive convexity assumptions on the system components, which are needed in the absence of a regularization term.

DOI 10.1007/s13235-022-00450-2

Cilt 13