D4Rl On D4Rl
Metrics
Average Reward
Results
Performance results of various models on this benchmark
Model Name | Average Reward | Paper Title | Repository |
|---|---|---|---|
| Performer | 63.8 | Rethinking Attention with Performers | - |
| Reformer | 63.9 | Reformer: The Efficient Transformer | - |
| cosFormer | 67.8 | cosFormer: Rethinking Softmax in Attention | - |
| PMDB | 88.2 | Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief | - |
| Linear Transformer | 64.4 | Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention | - |
| KFC | 81.8 | Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics | - |
| Flowformer | 73.5 | Flowformer: Linearizing Transformers with Conservation Flows | - |
| Primal.+DT | 77.5 | Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representation | - |
| Decision Transformer (DT) | 72.2 | Decision Transformer: Reinforcement Learning via Sequence Modeling | - |
0 of 9 row(s) selected.