Reinforcement Learning on CartPole Clean (test)
354,122Clean ReturnSat-EnQ
Evaluation results
| Method | Links | |
|---|---|---|
| Sat-EnQ2025.12 | 354,122 | |
| Double DQN2025.12 | 287,205 | |
| Bootstrapped DQN2025.12 | 268,195 | |
| DQN2025.12 | 249,238 |
| Method | Links | |
|---|---|---|
| Sat-EnQ2025.12 | 354,122 | |
| Double DQN2025.12 | 287,205 | |
| Bootstrapped DQN2025.12 | 268,195 | |
| DQN2025.12 | 249,238 |