Safe Reinforcement Learning on FormulaOne L2 (held-out seeds 10000–10019)
2Categorical Violation Rate (%)PPOLag
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| PPOLag2026.06 | 2 | 18 | — | — | |
| VLMPPOLag+Conf2026.06 | 8 | 18 | 2 | 2 |
Loading the SOTA2 catalog…
| Method | Links | ||||
|---|---|---|---|---|---|
| PPOLag2026.06 | 2 | 18 | — | — | |
| VLMPPOLag+Conf2026.06 | 8 | 18 | 2 | 2 |