Reinforcement Learning on pendulum discrete (Clean)
-28,087,189.02AUC@THFPS
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| HFPS2026.02 | -28,087,189.02 | -147.96 | 90 | -40 | |
| Dueling DQN2026.02 | -28,351,509.26 | -147.34 | — | — |
Loading the SOTA2 catalog…
| Method | Links | ||||
|---|---|---|---|---|---|
| HFPS2026.02 | -28,087,189.02 | -147.96 | 90 | -40 | |
| Dueling DQN2026.02 | -28,351,509.26 | -147.34 | — | — |