Reinforcement Learning on Acrobot (Best split)
99.1Normalized ScoreREFLEX
Evaluation results
| Method | Links | |
|---|---|---|
| REFLEXPolicy Type=Programmatic & Evolutionary Policies2026.06 | 99.1 | |
| DQNPolicy Type=Deep Reinforcement Learning2026.06 | 98.5 | |
| PPOPolicy Type=Deep Reinforcement Learning2026.06 | 98.5 | |
| MLESPolicy Type=Programmatic & Evolutionary Policies2026.06 | 98.4 | |
| Initial policyPolicy Type=Programmatic & Evolutionary Policies2026.06 | 6.8 |