ResearchBenchmarksReinforcement Learning on Inverted Pendulum Swingup (Average Episode Reward)Follow892.9Avg Episode RewardTRPO-55.6944190.5753436.845683.1147Nov 2, 2023Evaluation ResultsMethodMethodLinksAvg Episode RewardTRPO2023.11892.9TD32023.11892.25DSP2023.11891.9DDPG2023.11891.48SAC2023.11891.32ESPL2023.11890.36ACKTR2023.11890.11PPO2023.11890.1A2C2023.11254.71Regression2023.11-19.21