2 papers
cs.AI2024
Finding path and cycle counting formulae in graphs with Deep Reinforcement Learning
Jason Piquenot, Maxime Bérar, Pierre Héroux +3
This paper presents Grammar Reinforcement Learning (GRL), a reinforcement learning algorithm that uses Monte Carlo Tree Search (MCTS) and a transformer architecture that models a P…
cs.LG2023
Technical report: Graph Neural Networks go Grammatical
Jason Piquenot, Aldo Moscatelli, Maxime Bérar +4
This paper introduces a framework for formally establishing a connection between a portion of an algebraic language and a Graph Neural Network (GNN). The framework leverages Contex…