List your company

Continuous Control on MuJoCo Ant v4 (test)

6,665Mean Episodic ReturnFP-DRL
-273.881,527.563,3295,130.44Apr 1, 2026Apr 8, 2026Apr 16, 2026Apr 24, 2026May 2, 2026May 10, 2026May 18, 2026

Evaluation results

MethodLinks
FP-DRL2026.046,6650
DACER2026.045,971410
SAC-FLOW2026.045,3121,622
SAC2026.045,1791,408
DSAC-T2026.043,4991,081
TD32026.043,0230
RATArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.052,926.6—
PPOArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.051,373.9—
ACKTRArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.0523.4—
SophiaArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.05-7—