Statistical Comparison on OpenAI Gym LunarLander (Control Task)
-1.8707T-statisticPOEM
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| POEMtraining timesteps=250,000, experiments=10, evaluation episodes=15, baseline=PPO2026.01 | -1.8707 | 0.0778 | — |
| Method | Links | |||
|---|---|---|---|---|
| POEMtraining timesteps=250,000, experiments=10, evaluation episodes=15, baseline=PPO2026.01 | -1.8707 | 0.0778 | — |