Reproduce “Towards Optimal Inventory Control under Censored Demand: A Biased Sample-Average Approximation Approach” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yuxuan Han, Xiaoyu Fan, Jiawei Zhang, Zhengyuan Zhou
The authors develop algorithms for learning multi-period inventory policies when sales are censored by stock limits. They use directional bias in estimated demand distributions: DP-UCB favors lower stock targets for offline data, while DP-LCB raises online targets to reveal demand before reducing the bias. Under bounded costs and independent bounded demand, online regret scales as (h∞+b∞)MT√K, up to logarithmic and burn-in terms; coverage remains necessary.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.