Multi-objective Reinforcement Learning on MuJoCo Swimmer
3.187HypervolumePA2D-MORL
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| PA2D-MORL2026.03 | 3.187 | 0.55 | |
| PA2D-ablatedAblation=without PA-FT during training2026.03 | 2.965 | 0.603 | |
| PGMORL2026.03 | 2.566 | 0.917 | |
| PFAModification=modified version based on evolutionary framework2026.03 | 2.392 | 1.976 | |
| MOEA/DModification=modified version based on evolutionary framework2026.03 | 2.323 | 2.601 |