Offline Reinforcement Learning on D4RL Medium
49.1HalfCheetah ScoreDD
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| DDRuntime per action (second)=2.4352024.01 | 49.1 | 76.4 | 79.9 | 81.8 | |
| DiffuserLiteBackbone=D, Runtime per action (second)=0.022024.01 | 48.9 | 100.9 | 85.1 | 86 | |
| DiffuserLiteBackbone=R1, Runtime per action (second)=0.0142024.01 | 48.6 | 99.5 | 83.7 | 85.1 | |
| HDMI2024.01 | 48 | 106.4 | 88.8 | 82.6 | |
| IQL2024.01 | 47.4 | 66.3 | 79.7 | 77 | |
| DiffuserLiteBackbone=R2, Runtime per action (second)=0.0082024.01 | 45.3 | 96.8 | 88.1 | 81.9 | |
| DiffuserRuntime per action (second)=0.7492024.01 | 44.2 | 58.5 | 82.5 | 75.3 | |
| CQL2024.01 | 44 | 58.5 | 78.3 | 77.6 | |
| BC2024.01 | 42.6 | 52.9 | 75.3 | 51.9 |