InvertedPendulum
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Reinforcement Learning | InvertedPendulum v2 | Mean Reward1,000 | 27 | |
| Reinforcement Learning | InvertedPendulum v5 | Avg AUC (z-scored)1.77 | 13 | |
| Reinforcement Learning | InvertedPendulum | Mean Reward1,000 | 8 | |
| Continuous Control | InvertedPendulum v5 | Average Episodic Reward1,000 | 8 | |
| Imitation Learning from Observation | InvertedPendulum v4 | AER5.7 | 8 | |
| Continuous Control | InvertedPendulum v2 | Average Return1,000 | 7 | |
| Continuous Control | InvertedPendulum v1 (train) | Max Average Return1,000 | 7 | |
| Reinforcement Learning | InvertedPendulum Gymnasium | Mean Best Reward1,000 | 5 | |
| Continuous Control | InvertedPendulum MuJoCo v5 | Max Evaluation Return1,000 | 5 | |
| Policy Improvement | InvertedPendulum (IP) | Rate17 | 4 | |
| Reinforcement Learning | InvertedPendulum v4 | Average Episodic Reward1,000 | 4 |
Showing 11 of 11 rows