Strategizing against No-regret Learners

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Deng, Yuan, Schneider, Jon, Sivan, Balusubramanian
Format: Preprint
Published: 2019
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914147989454848
author Deng, Yuan
Schneider, Jon
Sivan, Balusubramanian
author_facet Deng, Yuan
Schneider, Jon
Sivan, Balusubramanian
contents How should a player who repeatedly plays a game against a no-regret learner strategize to maximize his utility? We study this question and show that under some mild assumptions, the player can always guarantee himself a utility of at least what he would get in a Stackelberg equilibrium of the game. When the no-regret learner has only two actions, we show that the player cannot get any higher utility than the Stackelberg equilibrium utility. But when the no-regret learner has more than two actions and plays a mean-based no-regret strategy, we show that the player can get strictly higher than the Stackelberg equilibrium utility. We provide a characterization of the optimal game-play for the player against a mean-based no-regret learner as a solution to a control problem. When the no-regret learner's strategy also guarantees him a no-swap regret, we show that the player cannot get anything higher than a Stackelberg equilibrium utility.
format Preprint
id arxiv_https___arxiv_org_abs_1909_13861
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle Strategizing against No-regret Learners
Deng, Yuan
Schneider, Jon
Sivan, Balusubramanian
Computer Science and Game Theory
Machine Learning
How should a player who repeatedly plays a game against a no-regret learner strategize to maximize his utility? We study this question and show that under some mild assumptions, the player can always guarantee himself a utility of at least what he would get in a Stackelberg equilibrium of the game. When the no-regret learner has only two actions, we show that the player cannot get any higher utility than the Stackelberg equilibrium utility. But when the no-regret learner has more than two actions and plays a mean-based no-regret strategy, we show that the player can get strictly higher than the Stackelberg equilibrium utility. We provide a characterization of the optimal game-play for the player against a mean-based no-regret learner as a solution to a control problem. When the no-regret learner's strategy also guarantees him a no-swap regret, we show that the player cannot get anything higher than a Stackelberg equilibrium utility.
title Strategizing against No-regret Learners
topic Computer Science and Game Theory
Machine Learning
url https://arxiv.org/abs/1909.13861