Reinforcement Learning Control on Gymnasium Pendulum v1
0.397MSI (s)DQN
Evaluation Results
| Method | Links | |
|---|---|---|
| DQNwc=102026.05 | 0.397 | |
| Pref-DQN (1 model)wc=162026.05 | 0.393 | |
| SACwc=102026.05 | 0.379 | |
| Classical STC (B3)2026.05 | 0.202 | |
| PPO2026.05 | 0.09 |
Loading the SOTA2 catalog…