link
Publish Date
Number
reflection
abstract
RL的可解释性问题：为啥采取这样的action。
基于此，将策略pi改写成了基于logic rule的differentiable形式。本来是黑箱决策，现在添加中间logic rules的显式调用。学习rule的方式和RNNLogic很像，都是现根据initial rules propose再学习weight，选择top-k rules
Status
Done
Type
induction
Author
Interpretable and Explainable Logical Policies
via Neurally Guided Symbolic Abstractionb
Words≈0 | Read Time ≈ 0 min
- Valine