Policy composition emerges from variational free energy minimization through a convergent gradient flow with a soft-competitive recurrent neural implementation.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Neural Policy Composition from Free Energy Minimization
Policy composition emerges from variational free energy minimization through a convergent gradient flow with a soft-competitive recurrent neural implementation.