A Regret Minimization Approach to Iterative Learning Control
Naman Agarwal 1 Elad Hazan 1 2 Anirudha Majumdar 1 2 Karan Singh 3
Abstract of factors. The primary challenge we focus on in this pa-
We consider the setting of iterative learning con- per is the existence of unmodeled deviations from nominal
trol, or model-based policy learning in the pres- dynamics, and external disturbances acting on the system.
ence of uncertain, time ...


雷达卡




京公网安备 11010802022788号







