Information Theoretic Regret Bounds for Online Nonlinear Control.

Sham M. Kakade Akshay Krishnamurthy Kendall Lowrey Motoya Ohnishi Wen Sun

Published in: NeurIPS (2020)

Keyphrases

information theoretic
information theory
mutual information
bregman divergences
online learning
log likelihood
regret bounds
kullback leibler divergence
online convex optimization