Saved in:
Bibliographic Details
Main Authors: Xiong, Yi, Chen, Ningyuan, Gao, Xuefeng
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.17463
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915517631037440
author Xiong, Yi
Chen, Ningyuan
Gao, Xuefeng
author_facet Xiong, Yi
Chen, Ningyuan
Gao, Xuefeng
contents When two players are engaged in a repeated game with unknown payoff matrices, they may use single-agent multi-armed bandit algorithms to choose the actions independent of each other. We show that when the players use Thompson sampling, the game dynamics converges to the Nash equilibrium under a mild assumption on the payoff matrices. Therefore, algorithmic collusion doesn't arise in this case despite the fact that the players do not intentionally deploy competitive strategies. To prove the convergence result, we find that the framework developed in stochastic approximation doesn't apply, because of the sporadic and infrequent updates of the inferior actions and the lack of Lipschitz continuity. We develop a novel sample-path-wise approach to show the convergence. However, when the payoff matrices do not satisfy the assumption, the game may converge to collusive outcomes.
format Preprint
id arxiv_https___arxiv_org_abs_2405_17463
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Is Thompson Sampling Susceptible to Algorithmic Collusion?
Xiong, Yi
Chen, Ningyuan
Gao, Xuefeng
Computer Science and Game Theory
Machine Learning
When two players are engaged in a repeated game with unknown payoff matrices, they may use single-agent multi-armed bandit algorithms to choose the actions independent of each other. We show that when the players use Thompson sampling, the game dynamics converges to the Nash equilibrium under a mild assumption on the payoff matrices. Therefore, algorithmic collusion doesn't arise in this case despite the fact that the players do not intentionally deploy competitive strategies. To prove the convergence result, we find that the framework developed in stochastic approximation doesn't apply, because of the sporadic and infrequent updates of the inferior actions and the lack of Lipschitz continuity. We develop a novel sample-path-wise approach to show the convergence. However, when the payoff matrices do not satisfy the assumption, the game may converge to collusive outcomes.
title Is Thompson Sampling Susceptible to Algorithmic Collusion?
topic Computer Science and Game Theory
Machine Learning
url https://arxiv.org/abs/2405.17463