| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| URL Benchmark Jaco | ICM | Reach Bottom Left9 | 12 | 4d ago | |
| URL Benchmark Quadruped | MOSS | Jump Score627 | 12 | 4d ago | |
| URL Benchmark (Walker) | RND | Flip Score237 | 12 | 4d ago | |
| ExORL jaco (4 tasks) zero-shot | ICVF | Average Return23 | 6 | 4d ago | |
| ExORL quadruped zero-shot | One-Step FB | Average Return645 | 6 | 4d ago | |
| ExORL cheetah (4 tasks) zero-shot | One-Step FB | Average Return378 | 6 | 4d ago | |
| ExORL walker (4 tasks) zero-shot | ICVF | Average Return619 | 6 | 4d ago | |
| DMC (DeepMind Control Suite) Maze | Soft FB_flow | Entropy H(Mπ_S)11.22 | 2 | 4d ago | |
| DMC (DeepMind Control Suite) Quadruped | Soft FB_flow | Entropy (State)14.43 | 2 | 4d ago | |
| DMC (DeepMind Control Suite) Cheetah | Soft FB_flow | Entropy H(Mπ_S)13.63 | 2 | 4d ago | |
| DMC (DeepMind Control Suite) Walker | Soft FB_flow | Entropy (State-Dependent Policy)13.97 | 2 | 4d ago |