Continuous Control on MuJoCo Humanoid v4
115Normalized Performance (Ret_nor)VDPO
Evaluation Results
| Method | Links | |
|---|---|---|
| VDPODelays=5, Global steps=1M2024.05 | 115 | |
| AD-SACDelays=5, Global steps=1M2024.05 | 98 | |
| BPQLDelays=5, Global steps=1M2024.05 | 96 | |
| DC/ACDelays=5, Global steps=1M2024.05 | 59 | |
| AD-SACDelays=25, Global steps=1M2024.05 | 25 | |
| A-SACDelays=5, Global steps=1M2024.05 | 13 | |
| BPQLDelays=25, Global steps=1M2024.05 | 12 | |
| VDPODelays=25, Global steps=1M2024.05 | 12 | |
| VDPODelays=50, Global steps=1M2024.05 | 12 | |
| AD-SACDelays=50, Global steps=1M2024.05 | 10 | |
| DIDADelays=5, Global steps=1M2024.05 | 8 | |
| BPQLDelays=50, Global steps=1M2024.05 | 8 | |
| DIDADelays=25, Global steps=1M2024.05 | 7 | |
| DIDADelays=50, Global steps=1M2024.05 | 7 | |
| A-SACDelays=25, Global steps=1M2024.05 | 5 | |
| DC/ACDelays=25, Global steps=1M2024.05 | 4 | |
| A-SACDelays=50, Global steps=1M2024.05 | 4 | |
| DC/ACDelays=50, Global steps=1M2024.05 | 3 |