FALCON incorporates psychologically grounded fatigue curves into learning-to-defer via a CMDP formulation and PPO-Lagrangian optimization, outperforming prior L2D methods and generalizing to unseen fatigue patterns on the new FA-L2D benchmark.
Constrained Markov decision processes with total cost criteria: Lagrangian approach and dual linear program.Mathematical methods of operations research, 48(3):387–417
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
-
Fatigue-Aware Learning to Defer via Constrained Optimisation
FALCON incorporates psychologically grounded fatigue curves into learning-to-defer via a CMDP formulation and PPO-Lagrangian optimization, outperforming prior L2D methods and generalizing to unseen fatigue patterns on the new FA-L2D benchmark.