Reinforcement Learning on ant 10-p
0.927Normalized ReturnIQL
Evaluation Results
| Method | Links | |
|---|---|---|
| IQL2026.02 | 0.927 | |
| Flex-f-Q2026.02 | 0.911 | |
| Flex-f-DICE2026.02 | 0.815 | |
| Opti-DICE2026.02 | 0.749 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| IQL2026.02 | 0.927 | |
| Flex-f-Q2026.02 | 0.911 | |
| Flex-f-DICE2026.02 | 0.815 | |
| Opti-DICE2026.02 | 0.749 |