ResearchBenchmarksReinforcement Learning on DMC Walker-runReinforcement Learning on DMC Walker-runFollow728.49Normalized AUCAltNet563.7436606.5143649.285692.0557Nov 30, 2025Evaluation resultsMethodMethodLinksNormalized AUCAltNetReplay Ratio (RR)=4Replay Ratio (RR)=42025.11728.49SRReplay Ratio (RR)=4Replay Ratio (RR)=42025.11725.44RDEReplay Ratio (RR)=4Replay Ratio (RR)=42025.11723.64SACReplay Ratio (RR)=4Replay Ratio (RR)=42025.11653.82AltNetReplay Ratio (RR)=1Replay Ratio (RR)=12025.11645.76RDEReplay Ratio (RR)=1Replay Ratio (RR)=12025.11643.22SRReplay Ratio (RR)=1Replay Ratio (RR)=12025.11617.06SACReplay Ratio (RR)=1Replay Ratio (RR)=12025.11570.08