Optimal sequential treatment allocation
This addresses risk-aware decision-making in sequential treatment settings, such as clinical trials or policy interventions, with incremental improvements in regret bounds.
The paper tackles the problem of sequential treatment allocation under uncertainty and risk concerns, proposing a policy that achieves minimax optimal regret and shows slow growth in suboptimal treatments.
In treatment allocation problems the individuals to be treated often arrive sequentially. We study a problem in which the policy maker is not only interested in the expected cumulative welfare but is also concerned about the uncertainty/risk of the treatment outcomes. At the outset, the total number of treatment assignments to be made may even be unknown. A sequential treatment policy which attains the minimax optimal regret is proposed. We also demonstrate that the expected number of suboptimal treatments only grows slowly in the number of treatments. Finally, we study a setting where outcomes are only observed with delay.