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.
Gradients are not all you need
4 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Differentiable relaxation of LTL automata via soft labeling enables gradient-based RL from formal specifications, with theoretical bounds on discrete-differentiable discrepancy and up to 2x returns on nonlinear tasks.
An end-to-end vision-based framework enables UAVs to traverse complex irregular gaps in unseen environments by mapping depth images to SE(3) control commands using differentiable simulation.
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.
-
Accelerated Learning with Linear Temporal Logic using Differentiable Simulation
Differentiable relaxation of LTL automata via soft labeling enables gradient-based RL from formal specifications, with theoretical bounds on discrete-differentiable discrepancy and up to 2x returns on nonlinear tasks.
-
Vision-Based End-to-End Learning for UAV Traversal of Irregular Gaps via Differentiable Simulation
An end-to-end vision-based framework enables UAVs to traverse complex irregular gaps in unseen environments by mapping depth images to SE(3) control commands using differentiable simulation.
- Differentiable hybrid force fields support scalable autonomous electrolyte discovery