Offline Rl On D4Rl
评估指标
Average Reward
评测结果
各个模型在此基准测试上的表现结果
模型名称 | Average Reward | Paper Title | Repository |
|---|---|---|---|
| Decision Transformer (DT) | 73.5 | Decision Transformer: Reinforcement Learning via Sequence Modeling | |
| KFC | 81.8 | Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics | - |
| ADMPO | 81 | Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning |
0 of 3 row(s) selected.