ResearchBenchmarksOffline Reinforcement Learning on half-me-morphOffline Reinforcement Learning on half-me-morphFollow45.3Performance ScoreIGDF33.23636.36839.542.632Dec 2, 2025Evaluation resultsMethodMethodLinksPerformance ScoreIGDFObservation Normalizat...Observation Normalization=false2025.1245.3DROCOObservation Normalizat...Observation Normalization=false2025.1243.4IQLObservation Normalizat...Observation Normalization=false2025.1237.2OTDFObservation Normalizat...Observation Normalization=false2025.1233.7