Reinforcement Learning of Sequential Price Mechanisms
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
Text
Brero et al. "Reinforcement Learning of Sequential Price Mechanisms." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I6.16659Markdown
[Brero et al. "Reinforcement Learning of Sequential Price Mechanisms." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/brero2021aaai-reinforcement/) doi:10.1609/AAAI.V35I6.16659BibTeX
@inproceedings{brero2021aaai-reinforcement,
title = {{Reinforcement Learning of Sequential Price Mechanisms}},
author = {Brero, Gianluca and Eden, Alon and Gerstgrasser, Matthias and Parkes, David C. and Rheingans-Yoo, Duncan},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2021},
pages = {5219-5227},
doi = {10.1609/AAAI.V35I6.16659},
url = {https://mlanthology.org/aaai/2021/brero2021aaai-reinforcement/}
}