<ul><li>Study focuses on online learning in generalized principal-agent model with strategic agents having private types and rewards.</li><li>Principal aims to learn optimal coordination mechanism to minimize strategic regret.</li><li>Developed sample-efficient algorithm using delaying mechanism, reward estimation framework, and LinUCB algorithm.</li><li>Established near-optimal regret bound for learning principal's optimal policy in the challenging setting.</li></ul>

Learning to Lead: Incentivizing Strategic Agents in the Dark

Discover more