| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Extrapolative Generalization | Walker-walk Unseen Dist. | Mean Reward231.73 | 5 | |
| Extrapolative Generalization | Walker-walk Unseen Gravity | Mean Reward499.91 | 5 | |
| Visual Walker Walk | Walker-walk DeepMind Control suite (expert) | Normalized Score61.1 | 5 | |
| Visual Walker Walk | Walker-walk DeepMind Control suite (medium-expert) | Normalized Score78.9 | 5 | |
| Visual Walker Walk | Walker-walk Medium DeepMind Control suite | Normalized Score61.7 | 5 | |
| Visual Walker Walk | Walker-walk DeepMind Control suite (medium-replay) | Normalized Score69.2 | 5 |