Reinforcement Learning on MuJoCo HalfCheetah v5
14,845Mean Episodic ReturnSAID
Evaluation Results
| Method | Links | |
|---|---|---|
| SAIDDelay steps=02026.03 | 14,845 | |
| SACDelay steps=02026.03 | 12,450 | |
| SAIDDelay steps=42026.03 | 9,648 | |
| SADRDelay steps=42026.03 | 8,190 | |
| VDPODelay steps=42026.03 | 6,720 | |
| SAIDDelay steps=82026.03 | 5,565 | |
| SAIDDelay steps=162026.03 | 5,289 | |
| SADRDelay steps=82026.03 | 4,945 | |
| DRDelay steps=42026.03 | 4,702 | |
| SADRDelay steps=162026.03 | 4,565 | |
| VDPODelay steps=82026.03 | 3,350 | |
| DRDelay steps=82026.03 | 2,873 | |
| VDPODelay steps=162026.03 | 2,085 | |
| DRDelay steps=162026.03 | 1,249 | |
| SACDelay steps=82026.03 | 129 | |
| SACDelay steps=162026.03 | 121 | |
| SACDelay steps=42026.03 | 109 |