Offline Reinforcement Learning on D4RL Medium-Expert
92.1HalfCheetah ScoreHDMI
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| HDMI2024.01 | 92.1 | 113.5 | 107.9 | 82.6 | |
| CQL2024.01 | 91.6 | 105.4 | 108.8 | 77.6 | |
| DiffuserLiteBackbone=R1, Runtime per action (second)=0.0142024.01 | 90.8 | 110.3 | 108.4 | 85.1 | |
| DDRuntime per action (second)=2.4352024.01 | 90.6 | 111.8 | 108.8 | 81.8 | |
| DiffuserLiteBackbone=D, Runtime per action (second)=0.022024.01 | 88.5 | 111.6 | 107.1 | 86 | |
| IQL2024.01 | 86.7 | 91.5 | 109.6 | 77 | |
| DiffuserLiteBackbone=R2, Runtime per action (second)=0.0082024.01 | 84 | 110.1 | 108.1 | 81.9 | |
| DiffuserRuntime per action (second)=0.7492024.01 | 79.8 | 107.2 | 108.4 | 75.3 | |
| BC2024.01 | 55.2 | 52.5 | 107.5 | 51.9 |