Offline Reinforcement Learning on AntMaze umaze (Normalized Average Return)
95.7Normalized Average ReturnVIPO-LEQ
Evaluation Results
| Method | Links | |
|---|---|---|
| VIPO-LEQ2025.04 | 95.7 | |
| LEQ2025.04 | 94.4 | |
| IQL-TD-MPC2025.04 | 52 | |
| MOBILE2025.04 | 0 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| VIPO-LEQ2025.04 | 95.7 | |
| LEQ2025.04 | 94.4 | |
| IQL-TD-MPC2025.04 | 52 | |
| MOBILE2025.04 | 0 |