• Citation: A. Koneru, P.S. Dutta, A. Muhammed, H. Chan, K. Balasubramanian, S. Manna, K. Sasikumar, P. Darancet, and S.K.R.S. Sankaranarayanan (2025), "Development and assessment of hierarchical multi-reward reinforcement learning based potential for silicene with state-of-the-art models", Materials Today Advances 26, 100583. DOI: 10.1016/j.mtadv.2025.100583.
    Abstract: We develop a new interatomic force field for Silicene, a 2D material with a buckled hexagonal lattice structure with high polymorphism. We introduce new parameterizations of a Tersoff model using a hierarchical multi-reward reinforcement learning (RL) methodology coupled with a continuous Monte Carlo Tree Search optimization. Our model significantly outperforms existing methods by enhancing the accuracy of predictions for the structural and thermodynamic properties of seven silicene polymorphs-including structure, energy, equation of state, elasticity, and phonon dispersion-when compared to established models. We further make a comprehensive comparison of the various models in predicting the mechanical and thermal properties of silicene. We trace the origin of the improved performance to the description of the angular dependence in the bond-order term, suggesting that modifying the angular terms in short-range models is essential to capture the structural diversity in low dimensional systems.

    Notes: This potential was developed to simulate the 2D phase silicene.

  • LAMMPS pair_style tersoff (2025--Koneru-A--Si--LAMMPS--ipr1)
    See Computed Properties
    Notes: This file was provided by Partha Sarathi Dutta on April 2, 2026.
    File(s):
Date Created: October 5, 2010 | Last updated: April 08, 2026