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

Robust Reinforcement Learning research benchmarks · SOTA2 Research

Robust Reinforcement Learning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Walker fixed exponential adversary MuJoCo

5,310Average Performance

12

Feb 26, 2026

HumanoidStandup fixed exponential adversary MuJoCo

129,966Avg Performance

12

Feb 26, 2026

Hopper fixed exponential adversary MuJoCo

3,036Average Performance

12

Feb 26, 2026

HalfCheetah fixed exponential adversary MuJoCo

8,256Avg Performance

12

Feb 26, 2026

Ant MuJoCo (fixed exponential adversary)

7,724Average Performance

12

Feb 26, 2026

Average-Reward Markov Decision Processes

2Sample Complexity

6

Jun 23, 2026

Popular datasets

halfcheetah hopper Ant Walker HumanoidStandup

Follow for updates

Join SOTA2 Contact