Optimistic no-regret learning converges pointwise to a Nash equilibrium in games with non-negative weighted regret, including harmonic games, when the equilibrium set is discrete.
Hedging in games: Faster convergence of external and swap regrets
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GT 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Pointwise Convergence in Games with Conflicting Interest
Optimistic no-regret learning converges pointwise to a Nash equilibrium in games with non-negative weighted regret, including harmonic games, when the equilibrium set is discrete.