A δ-window extension of Li et al.'s offline bandit evaluation lets logged actions near a policy's choice count, giving a biased but rank-preserving (at coarse level) way to compare continuous-armed bandit policies.
In: Advances in Neural Information Processing Systems, pp 1025--1033
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Exploring Offline Policy Evaluation for the Continuous-Armed Bandit Problem
A δ-window extension of Li et al.'s offline bandit evaluation lets logged actions near a policy's choice count, giving a biased but rank-preserving (at coarse level) way to compare continuous-armed bandit policies.