| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Locomotion | DeepMind Control suite Dog-Trot | Final Return938 | 17 | |
| Continuous Control | DeepMind Control Suite visual observations | Acrobot Swingup Score24,829 | 16 | |
| Continuous Control | DeepMind Control Suite (DMC) | Cheetah Run873 | 15 | |
| Continuous Control | DeepMind Control (DMC) Suite (1M steps) | IQM87.1 | 14 | |
| Walker-run | DeepMind Control Suite (DMC) | Average Return818 | 13 | |
| Walker-walk | DeepMind Control Suite (DMC) | Total Average Return988 | 13 | |
| Walker-stand | DeepMind Control Suite (DMC) | Total Return997 | 13 | |
| Dog-walk | DeepMind Control Suite (DMC) | Total Return976 | 13 | |
| Dog-run | DeepMind Control Suite (DMC) | Total Average Return628 | 13 | |
| Continuous Control | DeepMind Control Suite Cheetah Run | Reward836 | 13 | |
| Continuous Control | DeepMind Control Suite Reacher Hard (test) | Reward975.35 | 12 | |
| Continuous Control | DeepMind Control Suite Point Mass - Easy | Reward912.65 | 12 | |
| Hopper Hop | DeepMind Control Suite (DMC) | Steps Required (k)153.5 | 12 | |
| World model image prediction | DeepMind Control Suite Humanoid | MSE4.2077 | 12 | |
| Physical state prediction | DeepMind Control Suite Humanoid Easy tasks (random policy) | MSE0.6535 | 12 | |
| Physical state prediction | DeepMind Control Suite Reacher Easy tasks (random policy) | MSE0.0005 | 12 | |
| Physical state prediction | DeepMind Control Suite Cheetah Easy tasks (random policy) | MSE0.1206 | 12 | |
| Walker Run | DeepMind control suite | Average Return856 | 11 | |
| Hopper Hop | DeepMind control suite | Average Return511 | 11 | |
| Walker Run | DeepMind Control Suite (DMC) | Steps (k)512.6 | 10 | |
| Cup Catch | DeepMind Control Suite (DMC) | Sample Efficiency (Steps)104,700 | 10 | |
| World model image prediction | DeepMind Control Suite Acrobot | MSE0.1806 | 10 | |
| World model image prediction | DeepMind Control Suite Cheetah | MSE0.1565 | 10 | |
| Physical state prediction | DeepMind Control Suite Acrobot Easy tasks (random policy) | MSE0.0001 | 10 | |
| Walker Walk | DeepMind Control Suite (in-distribution) | Average Return996.502 | 10 |