Continuous Control on MuJoCo Humanoid v4 (test)
11,940Mean Episodic ReturnFP-DRL
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| FP-DRL2026.04 | 11,940 | 0 | |
| SAC-FLOW2026.04 | 10,017 | 0 | |
| RATArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.05 | 5,382.7 | — | |
| PPOArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.05 | 5,357.9 | — | |
| SAC2026.04 | 5,184 | 572 | |
| DACER2026.04 | 4,553 | 1,134 | |
| ACKTRArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.05 | 2,571.7 | — | |
| SophiaArchitecture=Shared actor-critic networks, Seeds=5 random seeds2026.05 | 669.4 | — | |
| DSAC-T2026.04 | 77 | 2 | |
| TD32026.04 | 69 | 0 |