Skip to content
conftrace_

variance-dependent regret bound

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

variance-dependent regret (1) horizon-free regret (1) linear mixture markov decision process (1) self-normalized martingale (1) heteroscedastic noise (1) linear contextual bandit (1) linear mixture mdp (1) linear bandit (1) online decision making (1)

Papers

Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency COLT 2023