Continuous Control on MountainCarContinuous v0
99.39Returnpi_ana
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| pi_anaPolicy Type=Analytical Solution2026.05 | 99.39 | — | 99.15 | 99.52 | 769 | — | |
| CH-3-ARSPolicy Type=Chebyshev Polynomial, Max-degree=3, Algorithm=ARS2026.05 | 98.74 | 0.65 | 98.95 | 99.11 | 471 | 0.152 | |
| CH-3-REIPolicy Type=Chebyshev Polynomial, Max-degree=3, Algorithm=REINFORCE2026.05 | 98.62 | 0.77 | 98.31 | 98.89 | 396 | 0.068 | |
| CH-3-PPOPolicy Type=Chebyshev Polynomial, Max-degree=3, Algorithm=PPO2026.05 | 98.1 | 1.29 | 97.61 | 98.42 | 469 | 0.087 | |
| ARSPolicy Type=Neural Policy (MLP), Algorithm=ARS2026.05 | 96.67 | 2.72 | 92.51 | 97.42 | 239 | 0.211 | |
| SACPolicy Type=Neural Policy (MLP), Algorithm=SAC2026.05 | 94.61 | 4.78 | 89.7 | 95.77 | 106 | 0.317 | |
| PPOPolicy Type=Neural Policy (MLP), Algorithm=PPO2026.05 | 93.91 | 5.48 | 90.86 | 95.23 | 298 | 0.273 |