ResearchBenchmarksReinforcement Learning on D4RL Kitchen (partial) (split 2)Reinforcement Learning on D4RL Kitchen (partial) (split 2)Follow63.7Normalized ReturnOPRIDE46.85251.22655.659.974Feb 19, 2026Evaluation resultsMethodMethodLinksNormalized ReturnOPRIDE2026.0263.7OPRL2026.0262.6PT+PDS2026.0249.8PT2026.0247.5