Multi-objective Reinforcement Learning on HalfCheetah 2
3.51HypervolumeMPFT-MOTD7
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| MPFT-MOTD72025.08 | 3.51 | 0.24 | 1.78 | 5,000,000 | |
| MPFT-MOSAC2025.08 | 3.25 | 1.48 | 1.72 | 7,800,000 | |
| MPFT-MOPPO2025.08 | 3.1 | 0.25 | 1.68 | 13,516,800 | |
| PA2D-MORL2025.08 | 3.09 | 0.03 | 1.67 | 41,943,040 | |
| PGMORL2025.08 | 3.04 | 0.13 | 1.66 | 41,943,040 | |
| C-MORL2025.08 | 2.93 | 0.02 | 1.61 | 41,943,040 |