Optimal Nonparametric Dynamic Pricing with Censored Demand and Adversarial Inventory
Threshold-UCB is developed, which improves the expected regret to $\widetilde{\mathcal{O}}(T^{2/3})$ and reuses sales observations across inventory levels through shared estimates of demand-tail probabilities, allowing the same data to support revenue upper bounds for multiple inventories rather than a single inventory...
Meng-Xiao Zhang, Ying-Fei Wang, Hai-Peng Luo
· 0 citations