Generalized Planning on Childsnack
100ScaleExplicitly regularized Q-value policy (Ω^Exp.)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Explicitly regularized Q-value policy (Ω^Exp.)Architecture=R-GNN2026.03 | 100 | 93 | |
| Heuristically regularized Q-value policy (Ω^Heu.)Architecture=R-GNN2026.03 | 100 | 93 | |
| Explicitly regularized Q-value policy (Ω^Exp.)Architecture=OAE2026.03 | 100 | 65.8 | |
| Heuristically regularized Q-value policy (Ω^Heu.)Architecture=OE2026.03 | 98 | 46.9 | |
| Heuristically regularized Q-value policy (Ω^Heu.)Architecture=OAE2026.03 | 83 | 41.5 | |
| Explicitly regularized Q-value policy (Ω^Exp.)Architecture=OE2026.03 | 82 | 43.1 | |
| State-value policy (V)Architecture=R-GNN2026.03 | 71 | 43.4 | |
| Vanilla Q-value policy (Q)Architecture=OAE2026.03 | 36 | 14.9 | |
| State-value policy (V)Architecture=OAE2026.03 | 31 | 15.9 | |
| State-value policy (V)Architecture=OE2026.03 | 26 | 12 | |
| Vanilla Q-value policy (Q)Architecture=R-GNN2026.03 | 16 | 4.2 | |
| Vanilla Q-value policy (Q)Architecture=OE2026.03 | 9 | 0.2 |