Kitchen Manipulation on D4RL Kitchen
91Success RateQ2RL
Evaluation Results
| Method | Links | |
|---|---|---|
| Q2RLData Availability=Without Data, Training Steps=300k2026.05 | 91 | |
| Q2RLData Availability=Without Data, Training Steps=200k2026.05 | 87 | |
| Q2RLData Availability=Without Data, Training Steps=100k2026.05 | 85 | |
| BC PolicyData Availability=Without Data, Training Steps=100k2026.05 | 69 | |
| BC PolicyData Availability=Without Data, Training Steps=200k2026.05 | 69 | |
| BC PolicyData Availability=Without Data, Training Steps=300k2026.05 | 69 | |
| WSRLData Availability=Without Data, Training Steps=200k2026.05 | 65 | |
| WSRLData Availability=Without Data, Training Steps=300k2026.05 | 64 | |
| IBRLData Availability=Without Data, Training Steps=300k2026.05 | 50 | |
| IBRLData Availability=Without Data, Training Steps=200k2026.05 | 43 | |
| IBRLData Availability=Without Data, Training Steps=100k2026.05 | 35 | |
| WSRLData Availability=Without Data, Training Steps=100k2026.05 | 31 | |
| CalQLData Availability=Without Data, Training Steps=300k2026.05 | 23 | |
| CalQLData Availability=Without Data, Training Steps=200k2026.05 | 19 | |
| CalQLData Availability=Without Data, Training Steps=100k2026.05 | 7 | |
| CQLData Availability=Without Data, Training Steps=300k2026.05 | 6 | |
| CQLData Availability=Without Data, Training Steps=100k2026.05 | 0 | |
| CQLData Availability=Without Data, Training Steps=200k2026.05 | 0 |