Reinforcement Learning on hammer human
340Normalized ReturnOpti-DICE
Evaluation results
| Method | Links | |
|---|---|---|
| Opti-DICE2026.02 | 340 | |
| Flex-f-Q2026.02 | 190 | |
| IQL2026.02 | 100 | |
| Flex-f-DICE2026.02 | 90 |
| Method | Links | |
|---|---|---|
| Opti-DICE2026.02 | 340 | |
| Flex-f-Q2026.02 | 190 | |
| IQL2026.02 | 100 | |
| Flex-f-DICE2026.02 | 90 |