| 1 |
Training Verifiably Robust Agents Using Set-Based Reinforcement Learning |
提出基于集合的强化学习方法，训练可验证鲁棒性的智能体 |
reinforcement learning |
|
|
| 2 |
QEDCartographer: Automating Formal Verification Using Reward-Free Reinforcement Learning |
QEDCartographer：利用无奖励强化学习自动化形式化验证 |
reinforcement learning |
|
|
| 3 |
Linear Attention is Enough in Spatial-Temporal Forecasting |
提出STformer与NSTformer以解决交通预测中的动态拓扑问题 |
linear attention |
✅ |
|
| 4 |
Markov Balance Satisfaction Improves Performance in Strictly Batch Offline Imitation Learning |
提出基于马尔可夫平衡的离线模仿学习方法，提升在严格批量环境下的性能 |
imitation learning |
|
|
| 5 |
Dynamic Graph Representation Learning for Passenger Behavior Prediction |
提出DyGPP，利用动态图学习预测乘客行为，助力智慧城市公共交通规划。 |
representation learning |
|
|
| 6 |
Fairness-Aware Streaming Feature Selection with Causal Graphs |
提出SFCF算法，利用因果图解决流式特征选择中的公平性与准确性权衡问题。 |
predictive model egocentric |
|
|