ResearchBenchmarksOffline Reinforcement Learning on half-e-kinematicOffline Reinforcement Learning on half-e-kinematicFollow34.7Performance ScoreDROCO12.54818.29924.0529.801Dec 2, 2025Evaluation resultsMethodMethodLinksPerformance ScoreDROCOObservation Normalizat...Observation Normalization=false2025.1234.7OTDFObservation Normalizat...Observation Normalization=false2025.1228.6IQLObservation Normalizat...Observation Normalization=false2025.1221.7IGDFObservation Normalizat...Observation Normalization=false2025.1213.4