Reinforcement Learning on lunarlander Noisy
-25,766,227.01AUC @ THFPS
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| HFPS2026.02 | -25,766,227.01 | 100.88 | 33.9 | 374.4 | |
| Double DQN2026.02 | -39,000,346.31 | -36.76 | — | — |
| Method | Links | ||||
|---|---|---|---|---|---|
| HFPS2026.02 | -25,766,227.01 | 100.88 | 33.9 | 374.4 | |
| Double DQN2026.02 | -39,000,346.31 | -36.76 | — | — |