List your company

Continuous Control on Inverted2Pendulum v5

9,352Final ReturnSAC
8,547.2488,756.1748,965.19,174.026Apr 10, 2026

Evaluation results

MethodLinks
SACNFE=12026.049,352
TD3NFE=12026.049,319.4
TRFP(ours)NFE=4 × 42026.049,304.1
TRFP(one-step)NFE=1 × 42026.049,304.1
SDACNFE=20 × 322026.048,794.3
MaxEntDPNFE=20 × 102026.048,578.2