PUSH
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Humanoid Locomotion | Push In-distribution (deterministic evaluation) | Cumulative Reward5.01 | 4 | |
| Reinforcement Learning | push 10-p | Normalized Return84.1 | 4 | |
| Reinforcement Learning | push 2-p | Normalized Return95.2 | 4 | |
| Reinforcement Learning | push 4-p | Normalized Return92.4 | 4 | |
| Video Prediction | PUSH1 | FVD630.4 | 4 |
Showing 5 of 5 rows