ResearchBenchmarksReinforcement Learning on MuJoCo Humanoid-Standup v2 (test)Reinforcement Learning on MuJoCo Humanoid-Standup v2 (test)Follow267,734.03Max Average ReturnMME133,847.3524168,606.3937203,365.435238,124.4763Jun 19, 2021Evaluation resultsMethodMethodLinksMax Average ReturnMME2021.06267,734.03DE-MME2021.06250,935.53SAC2021.06167,394.36PPO2021.06160,211.9TRPO2021.06153,919.84SQL2021.06138,996.84