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.
Michael Möller , abstract =
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
-
Hierarchical Reinforcement Learning for Sparse-Reward Search in Commutative Algebra
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.