ResearchBenchmarksReinforcement Learning on Hopper v5 (Terminal Performance and AUC)Follow270.9Terminal PerformanceRPIDDPG257.068260.659264.25267.841Jun 8, 2025Evaluation ResultsMethodMethodLinksTerminal PerformanceAUC (x10^6)RPIDDPG2025.06270.9241.5DDPG2025.06257.6219.3