Robustness of Anytime Bandit Policies
Antoine Salomon; Jean-Yves Audibert · 2011 · arXiv
WASTE classifies this as Negative / Null Result Report · AI classification, approximate
The study found no significant effect — useful as a negative control or null benchmark for your own design.
Abstract (excerpt)
This paper studies the deviations of the regret in a stochastic multi-armed bandit problem. When the total number of plays n is known beforehand by the agent, Audibert et al. (2009) exhibit a policy such that with probability at least 1-1/n, the regret of the policy is of order log(n). They have also shown that such a property is not shared by the popular ucb1 policy of Auer et al. (2002). This work first answers an open question: it extends this negative result to any anytime policy. The second contribution of this paper is to design anytime robust policies for specific multi-armed bandit pro
Excerpt shown for reference under fair use — read the full paper at the publisher.
About to run something similar?
Run an AI Precheck on your own design to catch failure modes like this one before you spend the time. Your first desk check is free.
Related failures
Channeling Fisher: Randomization Tests and the Statistical Insignificance of Seemingly Significant Experimental Results*
Negative / Null Result ReportThe harmonic mean p -value for combining dependent tests
Negative / Null Result ReportGeneralizability of heterogeneous treatment effect estimates across samples
Negative / Null Result ReportNumerical predictors of arithmetic success in grades 1–6
Negative / Null Result ReportMethods Matter: p-Hacking and Publication Bias in Causal Analysis in Economics
Negative / Null Result ReportShould multiple imputation be the method of choice for handling missing data in randomized trials?
WASTE indexes this work — it does not host or republish it. Failure-type classification is automated and approximate.
Metadata source: arXiv