Control Task on OpenAI Gym BipedalWalker (Statistical Comparison)
-2.0642T-statisticPOEM
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| POEMtraining timesteps=1,500,000, experiments=10, evaluation episodes=15, baseline=PPO2026.01 | -2.0642 | 0.0495 | — |
| Method | Links | |||
|---|---|---|---|---|
| POEMtraining timesteps=1,500,000, experiments=10, evaluation episodes=15, baseline=PPO2026.01 | -2.0642 | 0.0495 | — |