Reinforcement Learning on push 2-p
95.2Normalized ReturnIQL
Evaluation results
| Method | Links | |
|---|---|---|
| IQL2026.02 | 95.2 | |
| Flex-f-Q2026.02 | 95.2 | |
| Flex-f-DICE2026.02 | 93 | |
| Opti-DICE2026.02 | 87.4 |
| Method | Links | |
|---|---|---|
| IQL2026.02 | 95.2 | |
| Flex-f-Q2026.02 | 95.2 | |
| Flex-f-DICE2026.02 | 93 | |
| Opti-DICE2026.02 | 87.4 |