Generalized Planning on Ferry
100ScaleState-value policy (V)
Evaluation results
| Method | Links | ||
|---|---|---|---|
| State-value policy (V)Architecture=R-GNN2026.03 | 100 | 84.5 | |
| Explicitly regularized Q-value policy (Ω^Exp.)Architecture=R-GNN2026.03 | 100 | 85.2 | |
| Heuristically regularized Q-value policy (Ω^Heu.)Architecture=R-GNN2026.03 | 100 | 84.5 | |
| Explicitly regularized Q-value policy (Ω^Exp.)Architecture=OE2026.03 | 100 | 80.2 | |
| Heuristically regularized Q-value policy (Ω^Heu.)Architecture=OE2026.03 | 100 | 80.1 | |
| Explicitly regularized Q-value policy (Ω^Exp.)Architecture=OAE2026.03 | 100 | 79.5 | |
| Heuristically regularized Q-value policy (Ω^Heu.)Architecture=OAE2026.03 | 100 | 80.1 | |
| State-value policy (V)Architecture=OAE2026.03 | 45 | 26.4 | |
| State-value policy (V)Architecture=OE2026.03 | 33 | 19.8 | |
| Vanilla Q-value policy (Q)Architecture=R-GNN2026.03 | 30 | 12.9 | |
| Vanilla Q-value policy (Q)Architecture=OE2026.03 | 21 | 10.9 | |
| Vanilla Q-value policy (Q)Architecture=OAE2026.03 | 7 | 2.1 |