Multi-Objective Reinforcement Learning on MOBA
1.3302Hypervolume (HV)PPO
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| PPO2026.05 | 1.3302 | 0.4 | 2.307 | 0.788 | — | — | — | |
| MOPPOConditioned=Yes2026.05 | 0.3651 | 7.2 | 1.69 | 0.848 | 0.52 | 0.737 | 0.056 | |
| MOPPO (no cond.)Conditioned=No2026.05 | 0.3447 | 0.6 | 1.648 | 0.764 | — | — | — |