A differentiable DNF-based RL actor with a softmax-style activation can be trained end-to-end and then converted into editable ProbLog or ASP rule sets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Neural DNF-MT: A Neuro-symbolic Approach for Learning Interpretable and Editable Policies
A differentiable DNF-based RL actor with a softmax-style activation can be trained end-to-end and then converted into editable ProbLog or ASP rule sets.