ResearchBenchmarksReinforcement Learning on Ant v5 (Terminal Performance and AUC)Reinforcement Learning on Ant v5 (Terminal Performance and AUC)Follow208.2Terminal PerformanceRPIDDPG181.784188.642195.5202.358Jun 8, 2025Evaluation resultsMethodMethodLinksTerminal PerformanceAUC (Millions)RPIDDPG2025.06208.2163.4DDPG2025.06182.8144.4