ResearchBenchmarksContinuous Control on MuJoCo InvertedPendulum v4 (test)Follow1,000Mean Episodic ReturnFP-DRL-34.8233.85502.5771.15Apr 1, 2026Evaluation ResultsMethodMethodLinksMean Episodic ReturnStd Episodic ReturnFP-DRL2026.041,0005SAC2026.04941164DSAC-T2026.04860174TD32026.047780SAC-FLOW2026.04255DACER2026.0452