conftrace_

gap-dependent regret

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

adaptive multi-step bootstrap (1) monte carlo rollout (1) tabular markov decision process (1) tabular mdp (1) sub-optimality gap (1) gap-dependent regret bound (1) confidence interval (1) upper confidence bound (1)

Papers

Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap COLT 2021