Continuous Control on MuJoCo Swimmer standard (test)
271.6Episodic ReturnRAT
Evaluation Results
| Method | Links | |
|---|---|---|
| RATArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.05 | 271.6 | |
| PPOArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.05 | 191.3 | |
| ACKTRArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.05 | 59.1 | |
| SophiaArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.05 | 57.9 |