Reinforcement Learning on Acrobot (train)
98.5Normalized ScoreDQN
Evaluation results
| Method | Links | |
|---|---|---|
| DQNPolicy Type=Deep Reinforcement Learning2026.06 | 98.5 | |
| PPOPolicy Type=Deep Reinforcement Learning2026.06 | 98.5 | |
| REFLEXPolicy Type=Programmatic & Evolutionary Policies2026.06 | 98.5 | |
| MLESPolicy Type=Programmatic & Evolutionary Policies2026.06 | 97.8 | |
| Initial policyPolicy Type=Programmatic & Evolutionary Policies2026.06 | 5.3 |