List your company

Control Task on Inverted Pendulum (test)

996.35Average RewardPPO
125.3604351.4827577.605803.7273Feb 5, 2026

Evaluation results

MethodLinks
PPOVRER=true2026.02996.35
PPOVRER=false2026.02977.48
TRPOVRER=true2026.02962.76
TRPOVRER=false2026.02916.39
A2CVRER=true2026.02737.22
A2CVRER=false2026.02158.86