| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| D4RL 6 environments min-max normalized (averaged) | SMAC | Normalized Regret0.031 | 16 | 4d ago | |
| D4RL Antmaze | PEX | Avg Normalized Return91 | 15 | 4d ago | |
| D4RL Locomotion medium-expert | FamO2O | Average Normalized Return107.9 | 15 | 4d ago | |
| D4RL Locomotion medium | FamO2O | Average Normalized Return98.3 | 15 | 4d ago | |
| D4RL Locomotion medium-replay | FamO2O | Avg Normalized Return90.8 | 15 | 4d ago | |
| D4RL Locomotion random | FamO2O | Avg Normalized Return53.1 | 15 | 4d ago | |
| relocate | SMAC | Regret62.8 | 12 | 4d ago | |
| pen | SMAC | Regret5.3 | 12 | 4d ago | |
| door | SMAC | Regret50.3 | 12 | 4d ago | |
| walker2d | SMAC | Regret544.4 | 8 | 4d ago | |
| kitchen | CalQL/CQL | Regret256.6 | 8 | 4d ago | |
| hopper | SMAC | Regret353 | 8 | 4d ago | |
| D4RL walker2d | SMAC | Regret650.5 | 4 | 4d ago | |
| D4RL kitchen | SMAC | Regret131.4 | 4 | 4d ago | |
| D4RL hopper | CalQL/CQL | Regret293.7 | 4 | 4d ago |
