Decision Trees in Continuous Action Space for High-Throughput Exploration of Potential Energy Surface of Nanoclusters

The dynamic evolution of nanoclusters and temperature dependent stability and properties remain unexplored due to lack of their available force field. To mitigate this issue, we use a Monte Carlo Tree Search (MCTS) with reinforcement learning to develop potential models in a high throughput manner for nanoclusters of different element across the periodic table. To ensure the transferability of these parameters across different size regimes, we used an extensive training data set that encompasses structural and energetic properties of nanoclusters over a wide range of energy window. Our parameterized BOP model can accurately capture the structure, energetics, forces and dynamics of several different elemental clusters across the periodic table. This makes our newly developed scheme and the resulting models to be computationally robust but inexpensive tool for investigating a wide range of materials phenomena across a broad range of nanoclusters.