Multi-Objective Reinforcement Learning on Tetris
0.4284Hypervolume (HV)MOPPO
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| MOPPOConditioned=Yes2026.05 | 0.4284 | 23.4 | 5.817 | 0.716 | 0.874 | 0.733 | 0.695 | |
| PPO2026.05 | 0.1268 | 0.1 | 5.68 | 0.651 | — | — | — | |
| MOPPO (no cond.)Conditioned=No2026.05 | 0.1181 | 0 | 5.706 | 0.646 | — | — | — |