Multi-objective Reinforcement Learning on Walker2d-2
2.04Hypervolume (HV)MPFT-MOTD7
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| MPFT-MOTD72025.08 | 2.04 | 1.13 | 4.44 | 11,200,000 | |
| MPFT-MOSAC2025.08 | 1.72 | 1.52 | 4.01 | 16,400,000 | |
| MPFT-MOPPO2025.08 | 1.37 | 2.75 | 3.51 | 17,612,800 | |
| PA2D-MORL2025.08 | 1.31 | 0.32 | 3.47 | 41,943,040 | |
| C-MORL2025.08 | 1.21 | 0.57 | 3.29 | 41,943,040 | |
| PGMORL2025.08 | 1.11 | 2.02 | 3.25 | 41,943,040 |