BSI fits an environment simulator from bandit data and propagates parameter uncertainty to produce asymptotically valid confidence intervals for mean reward under arbitrary evaluation policies, including black-box adaptive ones.
Statistical inference under adaptive sampling with linucb.arXiv preprint arXiv:2512.00222,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Bandit Simulation for Average Reward Inference
BSI fits an environment simulator from bandit data and propagates parameter uncertainty to produce asymptotically valid confidence intervals for mean reward under arbitrary evaluation policies, including black-box adaptive ones.