List your company

ResearchFormerly WizWand

InvertedPendulum

Benchmarks

TaskDatasetSOTA resultTrendResults

Reinforcement Learning

InvertedPendulum v2

1,000Mean Reward

27

Reinforcement Learning

InvertedPendulum v5

1.77Avg AUC (z-scored)

13

Reinforcement Learning

InvertedPendulum

1,000Mean Reward

8

Continuous Control

InvertedPendulum v5

1,000Average Episodic Reward

8

Imitation Learning from Observation

InvertedPendulum v4

5.7AER

8

Continuous Control

InvertedPendulum v2

1,000Average Return

7

Continuous Control

InvertedPendulum v1 (train)

1,000Max Average Return

7

Reinforcement Learning

InvertedPendulum Gymnasium

1,000Mean Best Reward

5

Continuous Control

InvertedPendulum MuJoCo v5

1,000Max Evaluation Return

5

Policy Improvement

InvertedPendulum (IP)

17Rate

4

Reinforcement Learning

InvertedPendulum v4

1,000Average Episodic Reward

4