| 1 |
Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization |
提出上下文递归状态空间模型以解决零-shot泛化问题 |
reinforcement learning world model world models |
✅ |
|
| 2 |
Probabilistic World Modeling with Asymmetric Distance Measure |
提出非对称距离度量的概率世界建模方法以解决规划与推理问题 |
world model world models representation learning |
|
|
| 3 |
FlyKD: Graph Knowledge Distillation on the Fly with Curriculum Learning |
提出FlyKD以解决知识蒸馏中的伪标签优化问题 |
curriculum learning distillation |
|
|
| 4 |
Reinforcement Learning with Options and State Representation |
提出层次化强化学习方法以应对高维复杂环境问题 |
reinforcement learning policy learning |
|
|