Pole Balancing on CartPole Sim+Net
472Mean Episode ReturnFull Net-Aware
Evaluation Results
| Method | Links | |
|---|---|---|
| Full Net-AwareTraining Regime=Full Net-Aware2026.03 | 472 | |
| Delay-OnlyTraining Regime=Delay-Only2026.03 | 468 | |
| BaselineTraining Regime=Baseline2026.03 | 310 |