Multi-objective Reinforcement Learning on Hopper 2
3.68Hypervolume (HV)MPFT-MOTD7
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| MPFT-MOTD72025.08 | 3.68 | 1.55 | 5.85 | 19,200,000 | |
| MPFT-MOSAC2025.08 | 3.47 | 12 | 5.66 | 22,800,000 | |
| MPFT-MOPPO2025.08 | 3.37 | 2.66 | 5.44 | 27,033,600 | |
| PA2D-MORL2025.08 | 3.18 | 2.28 | 5.39 | 85,196,800 | |
| PGMORL2025.08 | 3.17 | 2.36 | 5.34 | 85,196,800 | |
| C-MORL2025.08 | 3.16 | 18.9 | 5.36 | 85,196,800 |