Reinforcement Learning on lunarlander Sticky
36,783,880.67AUC@THFPS
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| HFPS2026.02 | 36,783,880.67 | 244.08 | 34.1 | -6.8 | |
| Dueling DQN2026.02 | 27,439,517.04 | 261.87 | — | — |
| Method | Links | ||||
|---|---|---|---|---|---|
| HFPS2026.02 | 36,783,880.67 | 244.08 | 34.1 | -6.8 | |
| Dueling DQN2026.02 | 27,439,517.04 | 261.87 | — | — |