ResearchBenchmarksReinforcement Learning on DMC Quadruped-runReinforcement Learning on DMC Quadruped-runFollow717.24Normalized AUCRDE221.8776350.4813479.085607.6887Nov 30, 2025Evaluation resultsMethodMethodLinksNormalized AUCRDEReplay Ratio (RR)=4Replay Ratio (RR)=42025.11717.24AltNetReplay Ratio (RR)=4Replay Ratio (RR)=42025.11703.74SRReplay Ratio (RR)=4Replay Ratio (RR)=42025.11687.43AltNetReplay Ratio (RR)=1Replay Ratio (RR)=12025.11619.12RDEReplay Ratio (RR)=1Replay Ratio (RR)=12025.11609.36SRReplay Ratio (RR)=1Replay Ratio (RR)=12025.11568.36SACReplay Ratio (RR)=1Replay Ratio (RR)=12025.11377.27SACReplay Ratio (RR)=4Replay Ratio (RR)=42025.11240.93