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

InvertedDoublePendulum dataset and benchmarks · SOTA2 Research

Research Datasets

InvertedDoublePendulum

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Reinforcement Learning

InvertedDoublePendulum v5

1.29Avg AUC (z-scored)

13

Reinforcement Learning

InvertedDoublePendulum v3

9,360Average Final Return

7

Continuous Control

InvertedDoublePendulum v1 (train)

9,355.52Max Average Return

7

Reinforcement Learning

InvertedDoublePendulum Gymnasium

3,609.37Mean Best Reward

5

Reinforcement Learning Surrogate Modeling

InvertedDoublePendulum (IDP) (test)

103Reward Ratio (%)

4

Policy Improvement

InvertedDoublePendulum (IDP)

38Success Rate

4

Reinforcement Learning

InvertedDoublePendulum v4

9,167.5Average Episodic Reward

4

Continuous Control

InvertedDoublePendulum v5

9,349.2Average Episodic Reward

2

Popular tasks

Reinforcement Learning Continuous Control Policy improvement Reinforcement Learning Surrogate Modeling

Follow for updates

Join SOTA2 Contact