In bandit-feedback zero-sum games, uncoupled algorithms achieve last-iterate Nash convergence at the optimal rate of O(T^{-1/4}).
Zeroth-order learning in continuous games via residual pseudogradient estimates
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
ARGFree is the first gradient-free method for aggregative cooperative optimization, converging in expectation to an approximate solution via randomized finite differences and tracking, with a momentum-enhanced variant for high dimensions.
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}).
-
Model-Free Aggregative Cooperative Optimization via Randomized Gradient-Free Minimization and Exploration Momentum
ARGFree is the first gradient-free method for aggregative cooperative optimization, converging in expectation to an approximate solution via randomized finite differences and tracking, with a momentum-enhanced variant for high dimensions.