Reinforcement Learning on Lunar Lander (test)
84.6Normalized Win Score (NWS)PPO
Evaluation results
| Method | Links | |
|---|---|---|
| PPOPolicy Type=Deep Reinforcement Learning2026.06 | 84.6 | |
| REFLEXPolicy Type=Programmatic & Evolutionary Policies2026.06 | 82.2 | |
| MLESPolicy Type=Programmatic & Evolutionary Policies2026.06 | 81.9 | |
| EoHPolicy Type=Programmatic & Evolutionary Policies2026.06 | 77.6 | |
| Initial policyPolicy Type=Programmatic & Evolutionary Policies2026.06 | 65.3 | |
| DQNPolicy Type=Deep Reinforcement Learning2026.06 | 50.8 |