ResearchBenchmarksRobotic Control on Ant P-FLKFollow2,922.37Maximum Average ReturnMSAC295.642977.5811,659.522,341.459Sep 12, 2022Evaluation ResultsMethodMethodLinksMaximum Average ReturnMSACHistory Length=5History Length=52022.092,922.37LSTM-TD3History Length=5History Length=52022.092,658.81MTD3History Length=5History Length=52022.091,693.12TD32022.091,087.1SAC2022.09936.85PPO2022.09396.67