ResearchBenchmarksOffline Reinforcement Learning on D4RL Gym walker2d-randomFollow24.6Normalized ReturnSPQR0.3686.65912.9519.241Jan 6, 2024Evaluation ResultsMethodMethodLinksNormalized ReturnSPQRBase algorithm=SAC-MinBase algorithm=SAC-Min2024.0124.6SAC-Min2024.0121.7EDAC2024.0116.6CQL-Min2024.017BC2024.011.3