ResearchBenchmarksCross-Domain Offline Reinforcement Learning on MuJoCo Suite Aggregated All 24 tasks v2Follow1,612.9Total Normalized ScoreV2A1,108.3961,239.3731,370.351,501.327May 24, 2026Evaluation ResultsMethodMethodLinksTotal Normalized ScoreV2ABase Alignment=OTDFBase Alignment=OTDF2026.051,612.9V2ABase Alignment=IGDFBase Alignment=IGDF2026.051,562.5DVDFBase Alignment=OTDFBase Alignment=OTDF2026.051,395.9DVDFBase Alignment=IGDFBase Alignment=IGDF2026.051,374.7OTDF2026.051,319.5IGDF2026.051,286.7DARA2026.051,281.4IQL2026.051,249.7BOSA2026.051,127.8