| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Bottleneck | CPO | Episodic Reward388.1 | 8 | 4mo ago | |
| Grid | PPO-L | Episodic Reward276.3 | 8 | 4mo ago | |
| AntReach | CPO | Episodic Reward102.3 | 8 | 4mo ago | |
| PointReach | CPO | Episodic Reward89.2 | 8 | 4mo ago | |
| AntCircle | e-COP | Episodic Reward198.6 | 8 | 4mo ago | |
| PointCircle | e-COP | Episodic Reward110.5 | 8 | 4mo ago | |
| Humanoid | FOCOPS | Episodic Reward1,734.1 | 8 | 4mo ago | |
| Navigation | e-COP | Episodic Reward217.6 | 5 | 4mo ago | |
| MuJoCo Walker2d (eval) | FOCOPS | Reward2,455.3 | 4 | 24d ago | |
| MuJoCo Hopper eval environment | TraCeS | Reward1,610.7 | 4 | 24d ago | |
| MuJoCo HalfCheetah (eval) | FOCOPS | Reward2,951.7 | 4 | 24d ago | |
| MuJoCo Ant (eval) | FOCOPS | Reward3,177.6 | 4 | 24d ago | |
| Safety Gymnasium CarCircle2 (eval) | FOCOPS | Reward16 | 4 | 24d ago | |
| Safety Gymnasium CarCircle1 (val) | FOCOPS | Reward18.6 | 4 | 24d ago | |
| Safety Gymnasium PointCircle2 (eval) | CUP | Reward41.2 | 4 | 24d ago | |
| Episodic Constrained MDP | TRIPLE-Q | Violations0 | 1 | 4mo ago |
