| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Heterogeneous Pendulum Rich-Data 600,000 transition steps | AOC | Cumulative Reward-0.6 | 7 | 1mo ago | |
| Heterogeneous Pendulum 300,000 transition steps (Mid-Data) | AOC | Cumulative Reward-1.25 | 7 | 1mo ago | |
| Heterogeneous Pendulum Low-Data 100,000 transition steps | AOC | Cumulative Reward-1.39 | 7 | 1mo ago |