Reinforcement Learning on Lunar Lander (train)
1.09Normalized Win Score (NWS)MLES
Evaluation Results
| Method | Links | |
|---|---|---|
| MLESPolicy Type=Programmatic & Evolutionary Policies2026.06 | 1.09 | |
| REFLEXPolicy Type=Programmatic & Evolutionary Policies2026.06 | 1.082 | |
| EoHPolicy Type=Programmatic & Evolutionary Policies2026.06 | 1.053 | |
| PPOPolicy Type=Deep Reinforcement Learning2026.06 | 1.032 | |
| DQNPolicy Type=Deep Reinforcement Learning2026.06 | 1.017 | |
| Initial policyPolicy Type=Programmatic & Evolutionary Policies2026.06 | 0.629 |