Projected mini-batch policy gradient attains Õ(1/η) sample complexity for known C^s noise densities and Õ(η^{-(2s+1)/(2s)}) when the density must be estimated, by pairing observations to cancel the cusp-obstruction divergence.
Springer (2005)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Formalizes PCTL on MJLSs to specify and check moment-based stability properties for prescribed initial state sets using linear-algebraic techniques.
citing papers explorer
-
Stability Checking of Markov Jump Linear Systems via Probabilistic Temporal Logic (Extended Version)
Formalizes PCTL on MJLSs to specify and check moment-based stability properties for prescribed initial state sets using linear-algebraic techniques.