DiPRL trains nearly discrete programmatic policies in RL by adding architecture entropy regularization to gradient-based optimization, avoiding performance collapse from post-hoc discretization.
Learning to synthesize programs as interpretable and generalizable policies.Advances in Neural Information Processing Systems, 34:25146–25163
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DiPRL: Learning Discrete Programmatic Policies via Architecture Entropy Regularization
DiPRL trains nearly discrete programmatic policies in RL by adding architecture entropy regularization to gradient-based optimization, avoiding performance collapse from post-hoc discretization.