Multi-Objective Reinforcement Learning on D4MORL MO-Hopper Amateur
1.97Hypervolume (HV)Behavioral policy
Evaluation Results
| Method | Links | |
|---|---|---|
| Behavioral policy2025.08 | 1.97 | |
| MORvS2025.08 | 1.79 | |
| MOTD72025.08 | 1.73 | |
| MOSAC2025.08 | 1.58 | |
| CQL2025.08 | 1.02 |
Loading the SOTA2 catalog…