List your company

Continuous Control on MuJoCo Walker2d v4 (test)

3,156Episodic ReturnRAT
1,1801,6932,2062,719May 18, 2026

Evaluation results

MethodLinks
RATArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.053,156
ACKTRArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.052,576.6
PPOArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.052,225.3
SophiaArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.051,256