| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Safe Reinforcement Learning | Safety-Gymnasium PointPush (OSRL) | Cost0 | 48 | |
| Safe Reinforcement Learning | Safety-Gymnasium AntVelocity OSRL | Cost0 | 48 | |
| Safe Reinforcement Learning | Safety-Gymnasium CarCircle OSRL | Cost0 | 48 | |
| Safe Reinforcement Learning | Safety-Gymnasium PointGoal OSRL | Cost2.3 | 48 | |
| PointButton2 | Safety-Gymnasium | Normalized Reward58 | 21 | |
| PointButton1 | Safety-Gymnasium | Normalized Reward69 | 21 | |
| PointPush2 | Safety-Gymnasium | Normalized Reward44 | 21 | |
| PointPush1 | Safety-Gymnasium | Normalized Reward49 | 21 | |
| PointGoal2 | Safety-Gymnasium | Normalized Reward67 | 21 | |
| PointGoal1 | Safety-Gymnasium | Normalized Reward0.74 | 21 | |
| CarButton2 | Safety Gymnasium | Reward0.37 | 19 | |
| CarButton1 | Safety Gymnasium | Reward0.42 | 19 | |
| CarPush2 | Safety Gymnasium | Reward0.24 | 19 | |
| CarPush1 | Safety Gymnasium | Reward0.31 | 19 | |
| CarGoal2 | Safety Gymnasium | Reward0.65 | 19 | |
| CarGoal1 | Safety Gymnasium | Reward79 | 19 | |
| Button2 | Safety Gymnasium | Reward9.59 | 16 | |
| Button1 | Safety Gymnasium | Reward7.65 | 16 | |
| Goal2 | Safety Gymnasium | Reward11.48 | 16 | |
| Goal1 | Safety Gymnasium | Reward7.9 | 16 | |
| Safe Reinforcement Learning | Safety Gymnasium PointButton (C=25) | Return10.15 | 12 | |
| Safe Reinforcement Learning | Safety Gymnasium CarGoal (C=25) | Return27.7 | 12 | |
| Safe Reinforcement Learning | Safety Gymnasium CarButton (C=25) | Return1.13 | 12 | |
| Safe Reinforcement Learning | Safety Gymnasium Swimmer (C=25) | Return91.4 | 12 | |
| Safe Reinforcement Learning | Safety Gymnasium Hopper (C=25) | Return1,691.92 | 12 |