D4Rl On D4Rl
평가 지표
Average Reward
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | Average Reward |
|---|---|
| rethinking-attention-with-performers | 63.8 |
| reformer-the-efficient-transformer-1 | 63.9 |
| cosformer-rethinking-softmax-in-attention-1 | 67.8 |
| model-based-offline-reinforcement-learning | 88.2 |
| transformers-are-rnns-fast-autoregressive | 64.4 |
| koopman-q-learning-offline-reinforcement-1 | 81.8 |
| flowformer-linearizing-transformers-with | 73.5 |
| primal-attention-self-attention-through | 77.5 |
| decision-transformer-reinforcement-learning | 72.2 |