Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Generalized Planning on Rovers
Loading...
100
Scale
Explicitly regularized Q-value policy (Ω^Exp.)
18.88
39.94
61
82.06
Mar 18, 2026
Scale
SCov
Updated 1mo ago
Evaluation Results
Method
Method
Links
Scale
SCov
Explicitly regularized Q-value policy (Ω^Exp.)
Architecture=R-GNN
2026.03
100
66.5
Heuristically regularized Q-value policy (Ω^Heu.)
Architecture=R-GNN
2026.03
100
64.4
Heuristically regularized Q-value policy (Ω^Heu.)
Architecture=OAE
2026.03
61
29.8
Explicitly regularized Q-value policy (Ω^Exp.)
Architecture=OAE
2026.03
60
30.1
State-value policy (V)
Architecture=R-GNN
2026.03
53
29.8
Explicitly regularized Q-value policy (Ω^Exp.)
Architecture=OE
2026.03
48
24.6
Heuristically regularized Q-value policy (Ω^Heu.)
Architecture=OE
2026.03
46
23
Vanilla Q-value policy (Q)
Architecture=R-GNN
2026.03
36
17.1
Vanilla Q-value policy (Q)
Architecture=OE
2026.03
33
13.3
Vanilla Q-value policy (Q)
Architecture=OAE
2026.03
28
9.8
State-value policy (V)
Architecture=OE
2026.03
25
9.8
State-value policy (V)
Architecture=OAE
2026.03
22
8.3
Feedback
Search any
task
Search any
task