ResearchBenchmarksReinforcement Learning on Humanoid v2Follow8,048ReturnSAC-237.681,913.414,064.56,215.59Oct 1, 2019Evaluation ResultsMethodMethodLinksReturnSAC2019.108,048AWR2019.104,996DDPG2019.103,382PPO2019.10695TRPO2019.10552RWR2019.10509TD32019.1081