Offline Reinforcement Learning on Mixed Dataset Aggregate
62.2Normalized RewardMOBILE
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| MOBILEDataset Ratio (%)=502024.06 | 62.2 | 49.6 | — | — | |
| MOMBODataset Ratio (%)=502024.06 | 55.8 | 51.9 | — | — | |
| MOMBODataset Ratio (%)=102024.06 | 50.2 | 43.9 | — | — | |
| MOBILEDataset Ratio (%)=102024.06 | 48.5 | 41.3 | — | — | |
| MOPODataset Ratio (%)=502024.06 | 48 | 37.1 | — | — | |
| MOBILEDataset Ratio (%)=52024.06 | 38.4 | 35 | — | — | |
| MOMBODataset Ratio (%)=52024.06 | 37.4 | 35.8 | — | — | |
| MOMBODataset Ratio (%)=12024.06 | 37 | 29.5 | — | — | |
| MOPODataset Ratio (%)=102024.06 | 33.6 | 28.7 | — | — | |
| MOBILEDataset Ratio (%)=12024.06 | 32.4 | 28 | — | — | |
| MOPODataset Ratio (%)=52024.06 | 29.7 | 25.5 | — | — | |
| MOPODataset Ratio (%)=12024.06 | 27.9 | 23.5 | — | — | |
| MOBILEDataset Ratio (%)=All (Global Average)2024.06 | — | — | 45.4 | 2 | |
| MOBILEDataset Ratio (%)=All (AULC Global Average)2024.06 | — | — | 38.5 | 1.9 | |
| MOMBODataset Ratio (%)=All (Global Average)2024.06 | — | — | 45.1 | 1.5 | |
| MOMBODataset Ratio (%)=All (AULC Global Average)2024.06 | — | — | 40.3 | 1.5 | |
| MOPODataset Ratio (%)=All (Global Average)2024.06 | — | — | 34.8 | 2.5 | |
| MOPODataset Ratio (%)=All (AULC Global Average)2024.06 | — | — | 28.7 | 2.6 |