MINTS is a minimalist Bayesian algorithm for constrained bandits that attains Lai-Robbins regret in unstructured cases and sharp neighbor-based constants under unimodality.
arXiv preprint arXiv:2210.05660 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
KLinf-UCB is extended to nonparametric rewards with asymptotic expected-regret optimality and a tight upper bound on regret tail probability that recovers and matches prior results for bounded and finite-support cases.
citing papers explorer
-
MINTS: Minimalist Thompson Sampling
MINTS is a minimalist Bayesian algorithm for constrained bandits that attains Lai-Robbins regret in unstructured cases and sharp neighbor-based constants under unimodality.
-
Regret Tail Characterization of Optimal Bandit Algorithms with Generic Rewards
KLinf-UCB is extended to nonparametric rewards with asymptotic expected-regret optimality and a tight upper bound on regret tail probability that recovers and matches prior results for bounded and finite-support cases.