Weakly Consistent Optimal Pricing Algorithms in Repeated PostedPrice Auctions with Strategic Buyer
[edit]
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:13191328, 2018.
Abstract
We study revenue optimization learning algorithms for repeated postedprice auctions where a seller interacts with a single strategic buyer that holds a fixed private valuation for a good and seeks to maximize his cumulative discounted surplus. We propose a novel algorithm that never decreases offered prices and has a tight strategic regret bound of $\Theta(\log\log T)$. This result closes the open research question on the existence of a noregret horizonindependent weakly consistent pricing. We also show that the property of nondecreasing prices is nearly necessary for a weakly consistent algorithm to be a noregret one.
Related Material


