AV Rebalancing
35,725RewardMPC
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MPCRole=Oracle2026.06 | 35,725 | 3,203 | |
| Bi-level-learned2026.06 | 35,019 | 3,141 | |
| Bi-level-original2026.06 | 33,406 | 2,993 | |
| Inverse MPC2026.06 | 32,426 | 2,996 | |
| End-to-end RL2026.06 | 20,989 | 2,334.8 |
| Method | Links | ||
|---|---|---|---|
| MPCRole=Oracle2026.06 | 35,725 | 3,203 | |
| Bi-level-learned2026.06 | 35,019 | 3,141 | |
| Bi-level-original2026.06 | 33,406 | 2,993 | |
| Inverse MPC2026.06 | 32,426 | 2,996 | |
| End-to-end RL2026.06 | 20,989 | 2,334.8 |