#artificial intelligence
Sep 2025
Tackling GNARLy Problems: Graph Neural Algorithmic Reasoning Reimagined through Reinforcement Learning
This work reframe the problem of learning algorithm trajectories as a Markov decision process, which imposes structure on the solution construction procedure and unlocks the powerful tools of imitation and reinforcement learning (RL).
Alex Schutz, Victor-Alexandru Darvariu, Efimia Panagiotaki et al.
· arXiv.org · 1 citation