Reinforcement Learning on pendulum discrete Noisy
-26,282,013.77AUC@THFPS
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| HFPS2026.02 | -26,282,013.77 | -147.22 | 8.2 | 0.2 | |
| Dueling DQN2026.02 | -28,625,597.53 | -147.56 | — | — |
| Method | Links | ||||
|---|---|---|---|---|---|
| HFPS2026.02 | -26,282,013.77 | -147.22 | 8.2 | 0.2 | |
| Dueling DQN2026.02 | -28,625,597.53 | -147.56 | — | — |