| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Dataset 5 | AIRL | MSE0 | 13 | 4mo ago | |
| Dataset 4 | AIRL | MSE0 | 13 | 4mo ago | |
| Dataset 3 | AIRL | MSE0 | 13 | 4mo ago | |
| Dataset 2 | AIRL | MSE0 | 13 | 4mo ago | |
| Dataset 1 | AIRL | MSE0 | 13 | 4mo ago | |
| MuJoCo Walker | TRIRL | Normalized Return73 | 7 | 1mo ago | |
| MuJoCo Half Cheetah | SFM | Normalized Return1.07 | 7 | 1mo ago | |
| MuJoCo Ant | TRIRL | Normalized Return1.03 | 7 | 1mo ago | |
| HalfCheetah no disability (Target) | Mean Cumulative Reward6,420.38 | 6 | 1mo ago | ||
| HalfCheetah front disabled (Source) | Mean Cumulative Reward5,499.07 | 6 | 1mo ago | ||
| HalfCheetah rear disabled (Source) | Mean Cumulative Reward5,052.25 | 6 | 1mo ago | ||
| Half Cheetah (Target) | Mean Cumulative Reward6,420.38 | 6 | 1mo ago | ||
| Ant Leg 0,2 disabled (Target) | Mean Cumulative Reward3,590.57 | 6 | 1mo ago | ||
| Ant Leg 1,3 disabled (Target) | Mean Cumulative Reward3,369.05 | 6 | 1mo ago | ||
| Ant Leg 0,3 disabled (Source) | Mean Cumulative Rewards3,303.99 | 6 | 1mo ago | ||
| Ant Leg 1,2 disabled (Source) | Mean Cumulative Rewards3,312.12 | 6 | 1mo ago | ||
| Hopper | AIRL | Normalized Performance68 | 6 | 2mo ago | |
| Half Cheetah | TRIRL | Normalized Performance83 | 6 | 2mo ago | |
| Ant | TRIRL | Normalized Performance91 | 6 | 2mo ago | |
| Point Maze | TRIRL | Normalized Performance1.03 | 6 | 2mo ago | |
| D4RL Walker2d | DistIRL | Return1,526 | 6 | 3mo ago | |
| D4RL Hopper | Expert | Return892 | 6 | 3mo ago | |
| D4RL HalfCheetah | Expert | Return3,540 | 6 | 3mo ago | |
| D4RL HalfCheetah medium-expert | Expert | Return12,175 | 6 | 3mo ago | |
| D4RL Walker2d medium-expert | Expert | Return5,384 | 5 | 3mo ago |
