Skip to content
conftrace_

online regret bound

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

regret bound (2) undiscounted reinforcement learning (1) kernel methods (1) multiplicative update (1) winnow algorithm (1) upper confidence bound (1) multi-armed bandit (1) sparse linear regression (1) linear regression (1) optimal policy (1)

Papers

Winnowing with Gradient Descent COLT 2020 Logarithmic Online Regret Bounds for Undiscounted Reinforcement Learning NeurIPS 2006