Learning to Price Against a Moving Target
Abstract
In the Learning to Price setting, a seller posts prices over time with the goal of maximizing revenue while learning the buyer’s valuation. This problem is very well understood when values are stationary (fixed or iid). Here we study the problem where the buyer’s value is a moving target, i.e., they change over time either by a stochastic process or adversarially with bounded variation. In either case, we provide matching upper and lower bounds on the optimal revenue loss. Since the target is moving, any information learned soon becomes out-dated, which forces the algorithms to keep switching between exploring and exploiting phases.
Cite
Text
Leme et al. "Learning to Price Against a Moving Target." International Conference on Machine Learning, 2021.Markdown
[Leme et al. "Learning to Price Against a Moving Target." International Conference on Machine Learning, 2021.](https://mlanthology.org/icml/2021/leme2021icml-learning/)BibTeX
@inproceedings{leme2021icml-learning,
title = {{Learning to Price Against a Moving Target}},
author = {Leme, Renato Paes and Sivan, Balasubramanian and Teng, Yifeng and Worah, Pratik},
booktitle = {International Conference on Machine Learning},
year = {2021},
pages = {6223-6232},
volume = {139},
url = {https://mlanthology.org/icml/2021/leme2021icml-learning/}
}