Reinforcement Learning on half-cheetah 2-p
44.9Normalized ReturnIQL
Evaluation Results
| Method | Links | |
|---|---|---|
| IQL2026.02 | 44.9 | |
| Flex-f-Q2026.02 | 42.6 | |
| Flex-f-DICE2026.02 | 40.1 | |
| Opti-DICE2026.02 | 13.4 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| IQL2026.02 | 44.9 | |
| Flex-f-Q2026.02 | 42.6 | |
| Flex-f-DICE2026.02 | 40.1 | |
| Opti-DICE2026.02 | 13.4 |