The MVP algorithm achieves a gap-dependent variance-aware regret bound using a new conditional total variance measure, and a matching lower bound shows this variance dependence is necessary.
Navigating to the best policy in markov decision processes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs
The MVP algorithm achieves a gap-dependent variance-aware regret bound using a new conditional total variance measure, and a matching lower bound shows this variance dependence is necessary.