Reinforcement Learning on lunarlander Clean
42,642,395.61AUC@THFPS
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| HFPS2026.02 | 42,642,395.61 | 238.91 | 33.7 | -3.2 | |
| Double DQN2026.02 | 31,889,842.37 | 246.91 | — | — |
| Method | Links | ||||
|---|---|---|---|---|---|
| HFPS2026.02 | 42,642,395.61 | 238.91 | 33.7 | -3.2 | |
| Double DQN2026.02 | 31,889,842.37 | 246.91 | — | — |