Login / Signup
Variance-Aware Confidence Set: Variance-Dependent Bound for Linear Bandits and Horizon-Free Bound for Linear Mixture MDP.
Zihan Zhang
Jiaqi Yang
Xiangyang Ji
Simon S. Du
Published in:
CoRR (2021)
Keyphrases
</>
linear constraints
lower bound
upper bound
linear inequalities
linear functions
linear programming
covariance matrix
learning algorithm
mixture model
linear program
regret bounds
square loss