ResearchBenchmarksOffline Reinforcement Learning on half-me-morph MuJoCoOffline Reinforcement Learning on half-me-morph MuJoCoFollow49.2Normalized ScoreIGDF42.75244.42646.147.774Dec 2, 2025Evaluation resultsMethodMethodLinksNormalized ScoreIGDFObservation Normalizat...Observation Normalization=true, Observation Shift=morph2025.1249.2IQLObservation Normalizat...Observation Normalization=true, Observation Shift=morph2025.1246.4OTDFObservation Normalizat...Observation Normalization=true, Observation Shift=morph2025.1245.6DROCOObservation Normalizat...Observation Normalization=true, Observation Shift=morph2025.1243