Multi-objective Reinforcement Learning on MO-PointMaze 3obj
7.2ESRESR-IQL
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| ESR-IQL2026.06 | 7.2 | 12.03 | 10.17 | 87.16 | |
| AETDICEObjective optimized=ESR2026.06 | 6.79 | 11.76 | 10.15 | 86.05 | |
| AETDICEObjective optimized=BSR0.52026.06 | 4.72 | 12.04 | 11.14 | 120.34 | |
| Linear ScalarizationScalarization weights (w)=[0.75, 0.25]2026.06 | 0.38 | 2.41 | 2.2 | 198.15 | |
| Linear ScalarizationScalarization weights (w)=[1.0, 0.0]2026.06 | 0.34 | 2.49 | 2.17 | 203.2 | |
| Linear ScalarizationScalarization weights (w)=[0.5, 0.5]2026.06 | 0.26 | 10.61 | 12.27 | 176.92 | |
| AETDICEObjective optimized=SER2026.06 | 0.19 | 11.43 | 12.81 | 213.78 |