In generic finite leader-follower games the optimal Strong Stackelberg commitment is with probability one either pure and stable or mixed and unstable.
Regret minimization in stackelberg games with side information
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Algorithms achieve O(T^{1/2}) regret in contextual Stackelberg games via reduction to linear contextual bandits, improving on prior O(T^{2/3}) rates.
citing papers explorer
-
Pure or Unstable: A Generic Dichotomy for Strong Stackelberg Commitments
In generic finite leader-follower games the optimal Strong Stackelberg commitment is with probability one either pure and stable or mixed and unstable.
-
Nearly-Optimal Bandit Learning in Stackelberg Games with Side Information
Algorithms achieve O(T^{1/2}) regret in contextual Stackelberg games via reduction to linear contextual bandits, improving on prior O(T^{2/3}) rates.