Reinforcement Learning on half-cheetah 10-p
80.5Normalized ReturnOpti-DICE
Evaluation Results
| Method | Links | |
|---|---|---|
| Opti-DICE2026.02 | 80.5 | |
| Flex-f-Q2026.02 | 80.3 | |
| Flex-f-DICE2026.02 | 79.4 | |
| IQL2026.02 | 78.2 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| Opti-DICE2026.02 | 80.5 | |
| Flex-f-Q2026.02 | 80.3 | |
| Flex-f-DICE2026.02 | 79.4 | |
| IQL2026.02 | 78.2 |