Independent agents in a static mean-field game reach approximate Nash equilibrium under monotone payoffs, with finite-sample exploitability bounds for full and bandit feedback.
Theboundinthestatementofthetheoreminthemainbodyofthepaperfollowsfromthe fact that the lengths of the exploration epochs scale withTh = O(ε−1 log(h + 2)) = eO(ε−1)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Variational Inequality Approach to Independent Learning in Static Mean-Field Games
Independent agents in a static mean-field game reach approximate Nash equilibrium under monotone payoffs, with finite-sample exploitability bounds for full and bandit feedback.