Reinforcement Learning on pen cloned
58.9Normalized ReturnFlex-f-Q
Evaluation results
| Method | Links | |
|---|---|---|
| Flex-f-Q2026.02 | 58.9 | |
| IQL2026.02 | 56.2 | |
| Flex-f-DICE2026.02 | 40.4 | |
| Opti-DICE2026.02 | 22.9 |
| Method | Links | |
|---|---|---|
| Flex-f-Q2026.02 | 58.9 | |
| IQL2026.02 | 56.2 | |
| Flex-f-DICE2026.02 | 40.4 | |
| Opti-DICE2026.02 | 22.9 |