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

Adversarial Reinforcement Learning research benchmarks · SOTA2 Research

Adversarial Reinforcement Learning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Connect Four 100% optimal adversary (test-time)

-0.98Avg Return

3

Feb 26, 2026

Connect Four 70% optimal adversary (test)

0.02Average Return

3

Feb 26, 2026

Connect Four 50% optimal adversary (test-time)

0.11Average Return

3

Feb 26, 2026

Connect Four 30% optimal adversary (test-time)

0.55Average Return

3

Feb 26, 2026

Popular datasets

Follow for updates

Join SOTA2 Contact