SSP requires Omega(S A B_star^3 / (c_min epsilon^2)) samples in the worst case, with matching upper bounds that hold even for c_min=0 under bounded optimal hitting time.
Near-optimal time and sample complexities for solving markov decision processes with a generative model
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
-
Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model
SSP requires Omega(S A B_star^3 / (c_min epsilon^2)) samples in the worst case, with matching upper bounds that hold even for c_min=0 under bounded optimal hitting time.