Offline RL on D4RL
Metric: Average Reward (higher is better)
Metric: Average Reward (higher is better)
| # | Model↕ | Average Reward▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | KFC | 81.8 | No | Koopman Q-learning: Offline Reinforcement Learni... | 2021-11-02 | - |
| 2 | ADMPO | 81 | No | Any-step Dynamics Model Improves Future Predicti... | 2024-05-27 | Code |
| 3 | Decision Transformer (DT) | 73.5 | No | Decision Transformer: Reinforcement Learning via... | 2021-06-02 | Code |