| Paper | Code | Average Reward | ModelName | ReleaseDate |
|---|---|---|---|---|
| Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief | ✓ Link | 88.2 | PMDB | 2022-10-13 |
| Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics | 81.8 | KFC | 2021-11-02 | |
| Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representation | ✓ Link | 77.5 | Primal.+DT | 2023-05-31 |
| Flowformer: Linearizing Transformers with Conservation Flows | ✓ Link | 73.5 | Flowformer | 2022-02-13 |
| Decision Transformer: Reinforcement Learning via Sequence Modeling | ✓ Link | 72.2 | Decision Transformer (DT) | 2021-06-02 |
| cosFormer: Rethinking Softmax in Attention | ✓ Link | 67.8 | cosFormer | 2022-02-17 |
| Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention | ✓ Link | 64.4 | Linear Transformer | 2020-06-29 |
| Reformer: The Efficient Transformer | ✓ Link | 63.9 | Reformer | 2020-01-13 |
| Rethinking Attention with Performers | ✓ Link | 63.8 | Performer | 2020-09-30 |