A delayed, angle-estimation based LinUCB algorithm achieves \tilde O(sqrt T) strategic regret in a generalized principal-agent model with private types and non-myopic agents.
We make the convention thatχd−2 =eχd−2 =∞
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning to Lead: Incentivizing Strategic Agents in the Dark
A delayed, angle-estimation based LinUCB algorithm achieves \tilde O(sqrt T) strategic regret in a generalized principal-agent model with private types and non-myopic agents.