For a second-order plant with unknown gain and disturbance, a deployable student that learns only the inverse input gain from measured history nearly matches a privileged expert and beats a tuned observer by about 69% in unseen trials.
A reduction of imitation learning and structured pre- diction to no-regret online learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.SY 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
From Privileged Control to Deployable Adaptation:Fusing Mechanism-Guided Task Reduction with Learned Behavior
For a second-order plant with unknown gain and disturbance, a deployable student that learns only the inverse input gain from measured history nearly matches a privileged expert and beats a tuned observer by about 69% in unseen trials.