Reserve-Aware Contrast Certificates for Conservative Bandits with Uncertain Baselines
Conservative bandits must improve an incumbent policy without exhausting a prescribed performance budget. When the incumbent is uncertain, separately bounding candidate and baseline rewards can charge twice for shared estimation error. We develop Reserve-C4B around the baseline-relative contrast itself. A shared confidence set yields an exact expression for this avoidable penalty and a tighter…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
