In bandit-feedback zero-sum games, uncoupled algorithms achieve last-iterate Nash convergence at the optimal rate of O(T^{-1/4}).
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Log-barrier regularization in online mirror descent attains the optimal Õ(t^{-1/4}) last-iterate convergence rate in uncoupled zero-sum matrix games under bandit feedback.
citing papers explorer
-
The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback
In bandit-feedback zero-sum games, uncoupled algorithms achieve last-iterate Nash convergence at the optimal rate of O(T^{-1/4}).
-
Optimal last-iterate convergence in matrix games with bandit feedback using the log-barrier
Log-barrier regularization in online mirror descent attains the optimal Õ(t^{-1/4}) last-iterate convergence rate in uncoupled zero-sum matrix games under bandit feedback.