SHPRR: An Algorithm for Pure Exploration under Constrained Regret
Best Arm Identification (BAI) conventionally measures the cost of experimentation by the number of samples collected. In many operational settings, however, the cost of exploration relative to a trusted baseline already in place is equally important. We study BAI under both a fixed sampling horizon and a regret budget. Unlike generic resources considered in constrained pure exploration, regret…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
