Reinforcement Learning on MuJoCo Walker2d v5
5,222Mean Episodic ReturnSAID
Evaluation results
| Method | Links | |
|---|---|---|
| SAIDDelay steps=82026.03 | 5,222 | |
| SAIDDelay steps=02026.03 | 5,158 | |
| SADRDelay steps=82026.03 | 5,102 | |
| SADRDelay steps=42026.03 | 4,999 | |
| SAIDDelay steps=162026.03 | 4,913 | |
| SACDelay steps=02026.03 | 4,910 | |
| SAIDDelay steps=42026.03 | 4,874 | |
| SADRDelay steps=162026.03 | 4,827 | |
| VDPODelay steps=42026.03 | 4,494 | |
| VDPODelay steps=82026.03 | 4,323 | |
| VDPODelay steps=162026.03 | 3,032 | |
| DRDelay steps=82026.03 | 2,050 | |
| DRDelay steps=42026.03 | 1,979 | |
| DRDelay steps=162026.03 | 447 | |
| SACDelay steps=42026.03 | 338 | |
| SACDelay steps=82026.03 | 185 | |
| SACDelay steps=162026.03 | 157 |