Multi-objective Reinforcement Learning on Hopper 3
9.61Hypervolume (HV)MPFT-MOTD7
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| MPFT-MOTD72025.08 | 9.61 | 0.32 | 4.44 | 39,000,000 | |
| MPFT-MOSAC2025.08 | 8.54 | 2.03 | 4.37 | 41,600,000 | |
| PGMORL2025.08 | 7.62 | 4.85 | 4.3 | 135,168,000 | |
| MPFT-MOPPO2025.08 | 7.58 | 1.62 | 4.28 | 55,700,600 | |
| C-MORL2025.08 | 7.19 | 3.28 | 4.27 | 127,795,200 | |
| PA2D-MORL2025.08 | 6.73 | 3 | 4.21 | 135,168,000 |