Multi-Objective Reinforcement Learning on D4MORL MO-Hopper (Expert)
2.09HypervolumeBehavioral policy
Evaluation Results
| Method | Links | |
|---|---|---|
| Behavioral policy2025.08 | 2.09 | |
| MOTD72025.08 | 2.04 | |
| MORvS2025.08 | 1.98 | |
| MOSAC2025.08 | 1.87 | |
| CQL2025.08 | 1.56 |
Loading the SOTA2 catalog…