With opponent-action feedback in zero-sum games, an efficient algorithm achieves near-optimal t^{-1/2} last-iterate convergence in duality gap with high probability.
arXiv preprint arXiv:2406.13116 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Revenue of any ε-approximate correlated equilibrium in discrete first-price auctions is at least v₂ - Θ(1/k) - Θ(ε k²).
citing papers explorer
-
Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions
With opponent-action feedback in zero-sum games, an efficient algorithm achieves near-optimal t^{-1/2} last-iterate convergence in duality gap with high probability.
-
Revenue Guarantees of No-Swap-Regret Dynamics in First Price Auctions
Revenue of any ε-approximate correlated equilibrium in discrete first-price auctions is at least v₂ - Θ(1/k) - Θ(ε k²).