Continuous Control on Pendulum v1
-150.8Average Cumulative RewardCH-ARS
Evaluation Results
| Method | Links | |
|---|---|---|
| CH-ARSMax degree=6, Policy Type=Chebyshev2026.05 | -150.8 | |
| MA-MPPI2025.09 | -152.4 | |
| CH-PPOMax degree=5, Policy Type=Chebyshev2026.05 | -162.8 | |
| MPPI2025.09 | -165.8 | |
| PPOPolicy Type=MLP, Source=RL Baselines3 Zoo2026.05 | -176.2 | |
| MPC2025.09 | -188.3 | |
| SAC2025.09 | -192.6 | |
| PPO2025.09 | -205.1 | |
| DDPG2025.09 | -214.7 | |
| ARSPolicy Type=MLP, Source=RL Baselines3 Zoo2026.05 | -218.3 | |
| iLQR2025.09 | -258.9 |