Sign in
Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems.
Sahin Lale
Kamyar Azizzadenesheli
Babak Hassibi
Anima Anandkumar
Published in:
NeurIPS (2020)
Keyphrases
</>
partially observable
regret bounds
dynamical systems
linear dynamical systems
lower bound
online learning
linear regression
state space
upper bound
reinforcement learning
hidden markov models
np hard
computer vision
special case
active learning
infinite horizon
spatio temporal
bregman divergences
optimal solution