ResearchBenchmarksReinforcement Learning on Swimmer (Terminal Performance and AUC)Follow22.3Terminal PerformanceRPIDDPG19.28420.06720.8521.633Jun 8, 2025Evaluation ResultsMethodMethodLinksTerminal PerformanceAUC (x10^6)RPIDDPG2025.0622.321DDPG2025.0619.420.1