Generalized Planning on Logistics
100ScaleExplicitly regularized Q-value policy (Ω^Exp.)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Explicitly regularized Q-value policy (Ω^Exp.)Architecture=R-GNN2026.03 | 100 | 82.4 | |
| Heuristically regularized Q-value policy (Ω^Heu.)Architecture=R-GNN2026.03 | 100 | 84.3 | |
| Explicitly regularized Q-value policy (Ω^Exp.)Architecture=OE2026.03 | 100 | 86.2 | |
| Heuristically regularized Q-value policy (Ω^Heu.)Architecture=OE2026.03 | 100 | 85.7 | |
| Explicitly regularized Q-value policy (Ω^Exp.)Architecture=OAE2026.03 | 100 | 77 | |
| Heuristically regularized Q-value policy (Ω^Heu.)Architecture=OAE2026.03 | 100 | 75.6 | |
| Vanilla Q-value policy (Q)Architecture=OAE2026.03 | 57 | 31.2 | |
| Vanilla Q-value policy (Q)Architecture=OE2026.03 | 52 | 27 | |
| Vanilla Q-value policy (Q)Architecture=R-GNN2026.03 | 50 | 25.9 | |
| State-value policy (V)Architecture=R-GNN2026.03 | 47 | 24.9 | |
| State-value policy (V)Architecture=OAE2026.03 | 38 | 22.6 | |
| State-value policy (V)Architecture=OE2026.03 | 36 | 19.8 |