Share your thoughts, 1 month free Claude Pro on usSee more

Generalized Planning on Gripper

100Scale

State-value policy (V)

Updated 1mo ago

Evaluation Results

Method	Links
State-value policy (V) 2026.03		100	77.5
Explicitly regularized Q-value policy (Ω^Exp.) 2026.03		100	88.8
Heuristically regularized Q-value policy (Ω^Heu.) 2026.03		100	88.9
State-value policy (V) 2026.03		100	83
Explicitly regularized Q-value policy (Ω^Exp.) 2026.03		100	88.9
Heuristically regularized Q-value policy (Ω^Heu.) 2026.03		100	88.4
State-value policy (V) 2026.03		100	88.6
Vanilla Q-value policy (Q) 2026.03		100	73.8
Explicitly regularized Q-value policy (Ω^Exp.) 2026.03		100	88.5
Heuristically regularized Q-value policy (Ω^Heu.) 2026.03		100	88.6
Vanilla Q-value policy (Q) 2026.03		63	33.4
Vanilla Q-value policy (Q) 2026.03		36	15.2