Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Finding an ε-optimal policy from a single trajectory research benchmarks · SOTA2 Research

Finding an ε-optimal policy from a single trajectory

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Weakly communicating average-reward MDPs

-2Sample Complexity (Exponent on ε)

2

Jun 16, 2026

Communicating average-reward MDPs

-2Sample Complexity Exponent (vs ε)

1

Jun 16, 2026

Ergodic average-reward MDPs

-2Sample Complexity Exponent (vs ε)

1

Jun 16, 2026

Popular datasets

Ergodic average-reward MDPs Communicating average-reward MDPs Weakly communicating average-reward MDPs

Follow for updates

Join SOTA2 Contact