Generalized Planning on Visitall
961ScaleExplicitly regularized Q-value policy (Ω^Exp.)
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Explicitly regularized Q-value policy (Ω^Exp.)Architecture=R-GNN2026.03 | 961 | 25.1 | |
| Heuristically regularized Q-value policy (Ω^Heu.)Architecture=R-GNN2026.03 | 961 | 22.8 | |
| Explicitly regularized Q-value policy (Ω^Exp.)Architecture=OE2026.03 | 961 | 22.7 | |
| Heuristically regularized Q-value policy (Ω^Heu.)Architecture=OE2026.03 | 961 | 22.1 | |
| Explicitly regularized Q-value policy (Ω^Exp.)Architecture=OAE2026.03 | 961 | 24.8 | |
| Heuristically regularized Q-value policy (Ω^Heu.)Architecture=OAE2026.03 | 676 | 16.6 | |
| State-value policy (V)Architecture=OAE2026.03 | 529 | 13.4 | |
| Vanilla Q-value policy (Q)Architecture=OAE2026.03 | 484 | 14.9 | |
| State-value policy (V)Architecture=R-GNN2026.03 | 256 | 11.4 | |
| Vanilla Q-value policy (Q)Architecture=R-GNN2026.03 | 256 | 11.4 | |
| State-value policy (V)Architecture=OE2026.03 | 196 | 9.5 | |
| Vanilla Q-value policy (Q)Architecture=OE2026.03 | 144 | 5.7 |