Reinforcement Learning on push 10-p
84.1Normalized ReturnIQL
Evaluation Results
| Method | Links | |
|---|---|---|
| IQL2026.02 | 84.1 | |
| Flex-f-Q2026.02 | 81.3 | |
| Opti-DICE2026.02 | 69.5 | |
| Flex-f-DICE2026.02 | 68.4 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| IQL2026.02 | 84.1 | |
| Flex-f-Q2026.02 | 81.3 | |
| Opti-DICE2026.02 | 69.5 | |
| Flex-f-DICE2026.02 | 68.4 |