Hierarchical RL with equivariant GNN policies outperforms classical RL and greedy search when searching for counterexamples to an algebraic conjecture across a range of degrees.
Optimal Behavioral Hierarchy
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
EFE-based planning is formulated as variational free energy minimization with epistemic priors, decomposing into expected plan costs plus a complexity term.
citing papers explorer
-
Expected Free Energy-based Planning as Variational Inference
EFE-based planning is formulated as variational free energy minimization with epistemic priors, decomposing into expected plan costs plus a complexity term.