Safety-critical scenario generation on WOMD
0.915CRADV-BMT
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| ADV-BMTEvaluation Protocol=Dual-Stage [24], Evaluation Seeds=Average of 10 runs with varied seeds2026.03 | 0.915 | 0.324 | 0.251 | 0.603 | |
| SaFeREvaluation Protocol=Dual-Stage [24], Evaluation Seeds=Average of 10 runs with varied seeds2026.03 | 0.761 | 0.865 | 0.161 | 0.499 | |
| ReGentSEvaluation Protocol=Dual-Stage [24], Evaluation Seeds=Average of 10 runs with varied seeds2026.03 | 0.733 | 0.51 | 0.259 | 0.614 | |
| SAFE-SIMEvaluation Protocol=Dual-Stage [24], Evaluation Seeds=Average of 10 runs with varied seeds2026.03 | 0.616 | 0.549 | 0.197 | 0.508 | |
| FREAEvaluation Protocol=Dual-Stage [24], Evaluation Seeds=Average of 10 runs with varied seeds2026.03 | 0.536 | 0.719 | 0.213 | 0.566 |