ResearchBenchmarksContinuous Control on InvertedPendulum v1 (train)Follow1,000Max Average ReturnTD3984.816988.758992.7996.642Feb 26, 2018Evaluation ResultsMethodMethodLinksMax Average ReturnTD32018.021,000DDPG2018.021,000Our DDPG2018.021,000PPO2018.021,000ACKTR2018.021,000SAC2018.021,000TRPO2018.02985.4