| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Hopper sigma 0.3 (test) | Episode Reward1,368 | 24 | 3mo ago | ||
| Walker sigma 0.1 (test) | Episode Reward1,909 | 24 | 3mo ago | ||
| Half Cheetah sigma 0.3 (test) | DMAP | Episode Reward1,577 | 24 | 3mo ago | |
| Ant sigma 0.5 (test) | Oracle | Episode Reward974 | 24 | 3mo ago | |
| Ant sigma 0.3 (test) | Oracle | Episode Reward1,723 | 24 | 3mo ago | |
| Ant sigma 0.1 (test) | DMAP | Episode Reward2,240 | 24 | 3mo ago | |
| D4RL Walker2d medium-expert | Normalized Return111.2 | 23 | 3mo ago | ||
| Hopper sigma 0.7 (test) | DMAP | Episode Reward443 | 18 | 3mo ago | |
| Hopper sigma 0.5 (test) | DMAP | Episode Reward729 | 18 | 3mo ago | |
| Hopper sigma 0.1 (test) | RMA | Episode Reward1,859 | 18 | 3mo ago | |
| Walker sigma 0.7 (test) | DMAP | Episode Reward289 | 18 | 3mo ago | |
| Walker sigma 0.5 (test) | DMAP | Episode Reward518 | 18 | 3mo ago | |
| Walker sigma 0.3 (test) | Oracle | Episode Reward908 | 18 | 3mo ago | |
| Half Cheetah sigma 0.7 (test) | Reward462 | 18 | 3mo ago | ||
| Half Cheetah sigma 0.5 (test) | Episode Reward1,117 | 18 | 3mo ago | ||
| Half Cheetah sigma 0.1 (test) | Episode Reward2,278 | 18 | 3mo ago | ||
| Ant sigma 0.7 (test) | RMA | Episode Reward306 | 18 | 3mo ago | |
| D'Kitty 1% offline data | ExPT | Optimization Performance Score0.955 | 11 | 1mo ago | |
| Ant 1% offline data | OptBias | Optimization Performance Score96 | 11 | 1mo ago | |
| Cheetah-Dir-E (cr) | Average Return962.1 | 8 | 16d ago | ||
| DeepMind Control Suite (DMC) (test) | BiTAgent | Walker Stand Score103 | 7 | 3mo ago | |
| Hopper v5 | Evaluation Cost35.64 | 5 | 23d ago | ||
| MJPC Humanoid Walk (test) | WASP-Based iLQG | Speedup0.98 | 4 | 3mo ago | |
| MJPC Biped Balance (test) | WASP-Based iLQG | Speedup2.2 | 4 | 3mo ago | |
| MJPC Quadruped Gallop (test) | WASP-Based iLQG | Speedup4.04 | 4 | 3mo ago |
