Door Manipulation on D4RL Door
100Success RateWSRL
Evaluation Results
| Method | Links | |
|---|---|---|
| WSRLData Availability=Without Data, Training Steps=300k2026.05 | 100 | |
| WSRLData Availability=Without Data, Training Steps=200k2026.05 | 98 | |
| WSRLData Availability=Without Data, Training Steps=100k2026.05 | 91 | |
| Q2RLData Availability=Without Data, Training Steps=300k2026.05 | 87 | |
| Q2RLData Availability=Without Data, Training Steps=200k2026.05 | 73 | |
| Q2RLData Availability=Without Data, Training Steps=100k2026.05 | 55 | |
| BC PolicyData Availability=Without Data, Training Steps=100k2026.05 | 50 | |
| BC PolicyData Availability=Without Data, Training Steps=200k2026.05 | 50 | |
| BC PolicyData Availability=Without Data, Training Steps=300k2026.05 | 50 | |
| CQLData Availability=Without Data, Training Steps=300k2026.05 | 31 | |
| CalQLData Availability=Without Data, Training Steps=300k2026.05 | 15 | |
| CQLData Availability=Without Data, Training Steps=200k2026.05 | 2 | |
| CQLData Availability=Without Data, Training Steps=100k2026.05 | 0 | |
| CalQLData Availability=Without Data, Training Steps=100k2026.05 | 0 | |
| CalQLData Availability=Without Data, Training Steps=200k2026.05 | 0 | |
| IBRLData Availability=Without Data, Training Steps=100k2026.05 | 0 | |
| IBRLData Availability=Without Data, Training Steps=200k2026.05 | 0 | |
| IBRLData Availability=Without Data, Training Steps=300k2026.05 | 0 |