AIConfPaper
← Search

Jason Piquenot

2 accepted papers

2025

Grammar Reinforcement Learning: path and cycle counting in graphs with a Context-Free Grammar and Transformer approach

Jason Piquenot, Maxime Berar, Romain Raveaux, Pierre Héroux, Jean-Yves RAMEL, Sébastien Adam
ICLR 2025poster

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 Pushdown Automaton (PDA) within a context-free grammar (CFG) framework. Taking as use case the problem of efficiently cou…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

G$^2$N$^2$ : Weisfeiler and Lehman go grammatical

Jason Piquenot, Aldo Moscatelli, Maxime Berar, Pierre Héroux, Romain Raveaux, Jean-Yves RAMEL +1
ICLR 2024poster

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 Context-Free Grammars (CFG) to organize algebraic operations into generative rules that can be translated into a GNN layer mod…

Cited by 0Source ↗PDF ↗Scholar ↗