Reinforcement Learning on MuJoCo Hopper v5
3,268Mean Episodic ReturnSAID
Evaluation Results
| Method | Links | |
|---|---|---|
| SAIDDelay steps=162026.03 | 3,268 | |
| SAIDDelay steps=02026.03 | 3,170 | |
| SAIDDelay steps=42026.03 | 2,698 | |
| SAIDDelay steps=82026.03 | 2,514 | |
| SADRDelay steps=42026.03 | 2,405 | |
| SACDelay steps=02026.03 | 2,354 | |
| SADRDelay steps=162026.03 | 2,171 | |
| SADRDelay steps=82026.03 | 2,002 | |
| VDPODelay steps=42026.03 | 1,652 | |
| VDPODelay steps=162026.03 | 1,551 | |
| VDPODelay steps=82026.03 | 1,518 | |
| SACDelay steps=42026.03 | 188 | |
| DRDelay steps=42026.03 | 65 | |
| SACDelay steps=82026.03 | 61 | |
| SACDelay steps=162026.03 | 50 | |
| DRDelay steps=162026.03 | 34 | |
| DRDelay steps=82026.03 | 21 |