📊 Showing 3 results | 📏 Metric: Average Reward
| Rank | Model | Paper | Average Reward | Date | Code |
|---|---|---|---|---|---|
| 1 | KFC | Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics | 81.80 | 2021-11-02 | - |
| 2 | ADMPO | Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning | 81.00 | 2024-05-27 | 📦 HxLyn3/ADMPO |
| 3 | Decision Transformer (DT) | Decision Transformer: Reinforcement Learning via Sequence Modeling | 73.50 | 2021-06-02 | 📦 opendilab/DI-engine 📦 kzl/decision-transformer 📦 pytorch/rl |