Offline Reinforcement Learning on D4RL Kitchen manipulation v0
0.01Runtime (s)DiffuserLite-R2
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DiffuserLite-R2Backbone=rectified flow with reflow step2024.01 | 0.01 | 103.2 | |
| DiffuserLite-R1Backbone=rectified flow2024.01 | 0.015 | 66 | |
| DiffuserLite-DBackbone=diffusion model2024.01 | 0.017 | 58.7 | |
| HDMI2024.01 | 0.407 | 2.5 | |
| Diffuser2024.01 | 0.79 | 1.3 | |
| DD2024.01 | 2.573 | 0.4 |