List your company

Continuous Control on MuJoCo HumanoidStandup standard (test)

146,529.7Episodic ReturnRAT
109,799.916119,335.533128,871.15138,406.767May 18, 2026

Evaluation results

MethodLinks
RATArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.05146,529.7
PPOArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.05130,014.2
ACKTRArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.05127,928.5
SophiaArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.05111,212.6