Multi-objective Reinforcement Learning on MuJoCo HalfCheetah
5.787Hypervolume (HV)PA2D-MORL
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| PA2D-MORL2026.03 | 5.787 | 0.026 | |
| PGMORL2026.03 | 5.782 | 0.022 | |
| PFAModification=modified version based on evolutionary framework2026.03 | 5.765 | 0.548 | |
| PA2D-ablatedAblation=without PA-FT during training2026.03 | 5.741 | 0.106 | |
| MOEA/DModification=modified version based on evolutionary framework2026.03 | 5.739 | 0.679 |