Reinforcement Learning of Sequential Price Mechanisms
Computer Science and Game Theory
2021-05-07 v2 Artificial Intelligence
Machine Learning
Abstract
We introduce the use of reinforcement learning for indirect mechanisms, working with the existing class of sequential price mechanisms, which generalizes both serial dictatorship and posted price mechanisms and essentially characterizes all strongly obviously strategyproof mechanisms. Learning an optimal mechanism within this class forms a partially-observable Markov decision process. We provide rigorous conditions for when this class of mechanisms is more powerful than simpler static mechanisms, for sufficiency or insufficiency of observation statistics for learning, and for the necessity of complex (deep) policies. We show that our approach can learn optimal or near-optimal mechanisms in several experimental settings.
Cite
@article{arxiv.2010.01180,
title = {Reinforcement Learning of Sequential Price Mechanisms},
author = {Gianluca Brero and Alon Eden and Matthias Gerstgrasser and David C. Parkes and Duncan Rheingans-Yoo},
journal= {arXiv preprint arXiv:2010.01180},
year = {2021}
}