Continuous Control on Gymnasium Pendulum v1 (50x50 Initial Angles)
-147.24Return (R)SAC
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| SACsource=RL Baselines3 Zoo, architecture=MLP2026.05 | -147.24 | 83.39 | -377.46 | -1.08 | |
| TQCsource=RL Baselines3 Zoo, architecture=MLP2026.05 | -147.83 | 84.22 | -380.56 | -1.01 | |
| CH-6-ARSrepresentation=Chebyshev, max-degree=62026.05 | -150.8 | 88.12 | -392.02 | -0.21 | |
| TD3source=RL Baselines3 Zoo, architecture=MLP2026.05 | -155 | 92.71 | -377.14 | -0.51 | |
| DDPGsource=RL Baselines3 Zoo, architecture=MLP2026.05 | -156.64 | 106.5 | -1,491.25 | -1.26 | |
| CH-5-PPOrepresentation=Chebyshev, max-degree=52026.05 | -162.75 | 98.62 | -486.6 | -1.97 | |
| A2Csource=RL Baselines3 Zoo, architecture=MLP2026.05 | -167.9 | 102.09 | -528.22 | -0.08 | |
| PPOsource=RL Baselines3 Zoo, architecture=MLP2026.05 | -176.16 | 107.17 | -516.15 | -3.83 | |
| TRPOsource=RL Baselines3 Zoo, architecture=MLP2026.05 | -180.65 | 141.49 | -1,491.89 | -0.25 | |
| ARSsource=RL Baselines3 Zoo, architecture=MLP2026.05 | -218.32 | 159.3 | -784.63 | -0.07 |