The paper develops set-valued policies and conformal policy learning methods that output treatment sets with marginal coverage guarantees for robust decision-making under uncertainty.
Towards human-ai complementarity with prediction sets.Advances in Neural Information Processing Systems, 37:31380–31409
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Set-Valued Policy Learning
The paper develops set-valued policies and conformal policy learning methods that output treatment sets with marginal coverage guarantees for robust decision-making under uncertainty.