A quantile-of-means ensemble method achieves minimax optimal variance-dependent regret bounds for finite-horizon MDPs without count-based uncertainty estimates.
Improved Regret of Linear Ensemble Sampling , volume =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Quantile of Means: A Bonus-Free Ensemble Method for Minimax Optimal Reinforcement Learning
A quantile-of-means ensemble method achieves minimax optimal variance-dependent regret bounds for finite-horizon MDPs without count-based uncertainty estimates.