ResearchBenchmarksReinforcement Learning on Pusher v2Follow-19Average Final ReturnDACER-30.44-27.47-24.5-21.53May 24, 2024Evaluation ResultsMethodMethodLinksAverage Final ReturnDACER2024.05-19DSAC2024.05-19SAC2024.05-20TD32024.05-21TRPO2024.05-23PPO2024.05-23DDPG2024.05-30