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
比较表格
| 模型名称 | Average Reward |
|---|---|
| decision-transformer-reinforcement-learning | 73.5 |
| koopman-q-learning-offline-reinforcement-1 | 81.8 |
| any-step-dynamics-model-improves-future | 81 |
各个模型在此基准测试上的表现结果
| 模型名称 | Average Reward |
|---|---|
| decision-transformer-reinforcement-learning | 73.5 |
| koopman-q-learning-offline-reinforcement-1 | 81.8 |
| any-step-dynamics-model-improves-future | 81 |