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

Model-free learning on Toy 3-arm MDP benchmark leaderboard · SOTA2 Research

Research Benchmarks

Model-free learning on Toy 3-arm MDP

1Regret (T-dependence)Dig-DEC

Updated 4mo ago

Evaluation Results

Method	Links
Dig-DEC2025.10		1

SOTA Paper

Dig-DEC

An Improved Model-Free Decision-Estimation Coefficient with Applications in Adversarial MDPs

Dataset

Toy MDP

Follow for updates

Join SOTA2 Contact

Related Benchmarks

Model-free learning on Stochastic MDPs Bilinear or BE Regret Bound Estimation on Hybrid MDPs Bilinear setting Regret Bound Estimation on Hybrid MDPs (Bilinear or Coverable, Bellman Complete, On-Policy)