Introduction to multi-armed bandits

A Slivkins - Foundations and Trends® in Machine Learning, 2019‏ - nowpublishers.com
Multi-armed bandits a simple but very powerful framework for algorithms that make
decisions over time under uncertainty. An enormous body of work has accumulated over the …

The sample complexity of online contract design

B Zhu, S Bates, Z Yang, Y Wang, J Jiao… - arxiv preprint arxiv …, 2022‏ - arxiv.org
We study the hidden-action principal-agent problem in an online setting. In each round, the
principal posts a contract that specifies the payment to the agent based on each outcome …

A perspective on incentive design: Challenges and opportunities

LJ Ratliff, R Dong, S Sekar, T Fiez - Annual Review of Control …, 2019‏ - annualreviews.org
The increasingly tight coupling between humans and system operations in domains ranging
from intelligent infrastructure to e-commerce has led to a challenging new class of problems …

Crowdsourcing exploration

Y Papanastasiou, K Bimpikis… - Management Science, 2018‏ - pubsonline.informs.org
Motivated by the proliferation of online platforms that collect and disseminate consumers'
experiences with alternative substitutable products/services, we investigate the problem of …

Learning equilibria in matching markets from bandit feedback

M Jagadeesan, A Wei, Y Wang… - Advances in …, 2021‏ - proceedings.neurips.cc
Large-scale, two-sided matching platforms must find market outcomes that align with user
preferences while simultaneously learning these preferences from data. But since …

Bayesian exploration: Incentivizing exploration in Bayesian games

Y Mansour, A Slivkins, V Syrgkanis… - Operations …, 2022‏ - pubsonline.informs.org
We consider a ubiquitous scenario in the internet economy when individual decision makers
(henceforth, agents) both produce and consume information as they make strategic choices …

Bayesian incentive-compatible bandit exploration

Y Mansour, A Slivkins, V Syrgkanis - Proceedings of the Sixteenth ACM …, 2015‏ - dl.acm.org
Individual decision-makers consume information revealed by the previous decision makers,
and produce information that may help in future decision makers. This phenomenon is …

Rethinking search engines and recommendation systems: a game theoretic perspective

M Tennenholtz, O Kurland - Communications of the ACM, 2019‏ - dl.acm.org
Rethinking search engines and recommendation systems: a game theoretic perspective
Page 1 66 COMMUNICATIONS OF THE ACM | DECEMBER 2019 | VOL. 62 | NO. 12 review …

Bayesian incentive-compatible bandit exploration

Y Mansour, A Slivkins, V Syrgkanis - Operations Research, 2020‏ - pubsonline.informs.org
As self-interested individuals (“agents”) make decisions over time, they utilize information
revealed by other agents in the past and produce information that may help agents in the …

Bayesian exploration: Incentivizing exploration in bayesian games

Y Mansour, A Slivkins, V Syrgkanis, ZS Wu - arxiv preprint arxiv …, 2016‏ - arxiv.org
We consider a ubiquitous scenario in the Internet economy when individual decision-makers
(henceforth, agents) both produce and consume information as they make strategic choices …