Deep Learning Across Games

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Condorelli, Daniele, Furlan, Massimiliano
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913825878441984
author Condorelli, Daniele
Furlan, Massimiliano
author_facet Condorelli, Daniele
Furlan, Massimiliano
contents We train two neural networks adversarially to play static games. At each iteration, a row and column network observe a new random bimatrix game and output individual mixed strategies. The parameters of each network are independently updated via stochastic gradient descent on a loss defined by the individual squared regret experienced in the game. Simulations show the joint behavior of the trained networks approximates a Nash equilibrium in all games. In $2\times2$ games with multiple equilibria, the networks select the risk dominant equilibrium. These findings, which are robust and generalise out-of-distribution, illustrate how equilibrium emerges from learning across heterogeneous games.
format Preprint
id arxiv_https___arxiv_org_abs_2409_15197
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep Learning Across Games
Condorelli, Daniele
Furlan, Massimiliano
Theoretical Economics
We train two neural networks adversarially to play static games. At each iteration, a row and column network observe a new random bimatrix game and output individual mixed strategies. The parameters of each network are independently updated via stochastic gradient descent on a loss defined by the individual squared regret experienced in the game. Simulations show the joint behavior of the trained networks approximates a Nash equilibrium in all games. In $2\times2$ games with multiple equilibria, the networks select the risk dominant equilibrium. These findings, which are robust and generalise out-of-distribution, illustrate how equilibrium emerges from learning across heterogeneous games.
title Deep Learning Across Games
topic Theoretical Economics
url https://arxiv.org/abs/2409.15197