Power Grid Control on Grid2Op 100 held-out episodes (val)
5,584Mean RewardDecision tree
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Decision treeModel type=Distilled student2026.05 | 5,584 | 7,109.9 | 2,253.3 | 595.7 | |
| Random forestModel type=Distilled student2026.05 | 5,580.6 | 7,109.7 | 2,251.9 | 595.7 | |
| PPO2026.05 | 4,529.9 | 5,321.5 | 2,489.7 | 589.9 | |
| DoNothing2026.05 | 1,821.5 | 1,238.2 | 1,627.1 | -9 |