New GLR and GSR tests for unknown pre- and post-change reward distributions achieve order-optimal logarithmic latency in piecewise stationary bandits.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IT 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Sequential Change Detection for Learning in Piecewise Stationary Bandit Environments
New GLR and GSR tests for unknown pre- and post-change reward distributions achieve order-optimal logarithmic latency in piecewise stationary bandits.