ResearchBenchmarksPolicy generalization on MESSENGER-WM NewAll (test)Follow1.16Average Sum of ScoresLED-WM0.08880.36690.6450.9231Nov 28, 2025Evaluation ResultsMethodMethodLinksAverage Sum of ScoresLED-WM2025.111.16EMMA-LWMTraining protocol=Onli...Training protocol=Online IL2025.110.62EMMA-LWMTraining protocol=Filt...Training protocol=Filtered BC (near-optimal)2025.110.44EMMA-LWMTraining protocol=Filt...Training protocol=Filtered BC (suboptimal)2025.110.13