Reinforcement Learning on Lunar Lander (Best split)
1.098Normalized Win Score (NWS)MLES
Evaluation Results
| Method | Links | |
|---|---|---|
| MLESPolicy Type=Programmatic & Evolutionary Policies2026.06 | 1.098 | |
| REFLEXPolicy Type=Programmatic & Evolutionary Policies2026.06 | 1.092 | |
| EoHPolicy Type=Programmatic & Evolutionary Policies2026.06 | 1.085 | |
| PPOPolicy Type=Deep Reinforcement Learning2026.06 | 1.076 | |
| DQNPolicy Type=Deep Reinforcement Learning2026.06 | 1.066 | |
| Initial policyPolicy Type=Programmatic & Evolutionary Policies2026.06 | 0.629 |