Reinforcement Learning on LunarLanderContinuous v3
308.03Mean ScoreZIG-EDA
Evaluation results
| Method | Links | ||
|---|---|---|---|
| ZIG-EDAGenerations=1002026.06 | 308.03 | 3.51 | |
| Sparse EAGenerations=1002026.06 | 303.59 | 4.73 | |
| Dense EDAGenerations=1002026.06 | 301.63 | 7.71 | |
| Ad-hoc sparse EDAGenerations=1002026.06 | 293.69 | 13.18 |