List your company

Continuous Control on MuJoCo Swimmer standard (test)

271.6Episodic ReturnRAT
49.352107.051164.75222.449May 18, 2026

Evaluation results

MethodLinks
RATArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.05271.6
PPOArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.05191.3
ACKTRArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.0559.1
SophiaArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.0557.9