A new no-prior-knowledge model-free algorithm achieves O~( |S||A| ||h*||^2_sp / eps^2 ) sample complexity for weakly communicating average-reward MDPs, matching the lower bound up to a factor ||h*||_sp.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Near-Optimal Sample Complexity for MDPs via Anchoring
A new no-prior-knowledge model-free algorithm achieves O~( |S||A| ||h*||^2_sp / eps^2 ) sample complexity for weakly communicating average-reward MDPs, matching the lower bound up to a factor ||h*||_sp.