Multi-objective Reinforcement Learning on Ant 2
7.04HypervolumeMPFT-MOTD7
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| MPFT-MOTD72025.08 | 7.04 | 1.18 | 2.47 | 19,200,000 | |
| MPFT-MOSAC2025.08 | 3.75 | 5.63 | 1.77 | 22,800,000 | |
| C-MORL2025.08 | 0.94 | 1.86 | 0.92 | 85,196,800 | |
| PA2D-MORL2025.08 | 0.87 | 1.36 | 0.88 | 85,196,800 | |
| PGMORL2025.08 | 0.68 | 2.32 | 0.79 | 85,196,800 | |
| MPFT-MOPPO2025.08 | 0.43 | 1.32 | 0.54 | 24,576,000 |