Reinforcement learning for in silico determination of adsorbate: substrate structures
Reinforcement learning (RL) methods have helped to define the state of the art in the field of modern artificial intelligence, mostly after the breakthrough involving AlphaGo and the discovery of novel algorithms. In this work, we present a RL method, based on Q-learning, for the structural determin...
Published in: | Journal of Computational Chemistry |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Wiley
2024
|
Subjects: | |
Online Access: | https://doi.org/10.1002/jcc.27322 https://nrc-publications.canada.ca/eng/view/object/?id=520f0a4d-de3b-4e83-ba8c-63153ebb5c8e https://nrc-publications.canada.ca/fra/voir/objet/?id=520f0a4d-de3b-4e83-ba8c-63153ebb5c8e |
id |
ftnrccanada:oai:cisti-icist.nrc-cnrc.ca:cistinparc:520f0a4d-de3b-4e83-ba8c-63153ebb5c8e |
---|---|
record_format |
openpolar |
spelling |
ftnrccanada:oai:cisti-icist.nrc-cnrc.ca:cistinparc:520f0a4d-de3b-4e83-ba8c-63153ebb5c8e 2024-09-15T18:29:00+00:00 Reinforcement learning for in silico determination of adsorbate: substrate structures Lourenço, Maicon Pierre Hostaš, Jiří Bellinger, Colin Tchagang, Alain Salahub, Dennis R. 2024-02-15 text https://doi.org/10.1002/jcc.27322 https://nrc-publications.canada.ca/eng/view/object/?id=520f0a4d-de3b-4e83-ba8c-63153ebb5c8e https://nrc-publications.canada.ca/fra/voir/objet/?id=520f0a4d-de3b-4e83-ba8c-63153ebb5c8e eng eng Wiley issn:0192-8651 issn:1096-987X Journal of Computational Chemistry, Publication date: 2024-02-15 doi:10.1002/jcc.27322 adsorption DFT DFTB functional materials reinforcement learning transfer-learning article 2024 ftnrccanada https://doi.org/10.1002/jcc.27322 2024-08-05T14:05:07Z Reinforcement learning (RL) methods have helped to define the state of the art in the field of modern artificial intelligence, mostly after the breakthrough involving AlphaGo and the discovery of novel algorithms. In this work, we present a RL method, based on Q-learning, for the structural determination of adsorbate@substrate models in silico, where the minimization of the energy landscape resulting from adsorbate interactions with a substrate is made by actions on states (translations and rotations) chosen from an agent's policy. The proposed RL method is implemented in an early version of the reinforcement learning software for materials design and discovery (RLMaterial), developed in Python3.x. RLMaterial interfaces with deMon2k, DFTB+, ORCA, and Quantum Espresso codes to compute the adsorbate@substrate energies. The RL method was applied for the structural determination of (i) the amino acid glycine and (ii) 2-amino-acetaldehyde, both interacting with a boron nitride (BN) monolayer, (iii) host-guest interactions between phenylboronic acid and β-cyclodextrin and (iv) ammonia on naphthalene. Density functional tight binding calculations were used to build the complex search surfaces with a reasonably low computational cost for systems (i)–(iii) and DFT for system (iv). Artificial neural network and gradient boosting regression techniques were employed to approximate the Q-matrix or Q-table for better decision making (policy) on next actions. Finally, we have developed a transfer-learning protocol within the RL framework that allows learning from one chemical system and transferring the experience to another, as well as from different DFT or DFTB levels. In press: Yes Peer reviewed: Yes NRC publication: Yes Article in Journal/Newspaper Orca National Research Council Canada: NRC Publications Archive Journal of Computational Chemistry 45 15 1289 1302 |
institution |
Open Polar |
collection |
National Research Council Canada: NRC Publications Archive |
op_collection_id |
ftnrccanada |
language |
English |
topic |
adsorption DFT DFTB functional materials reinforcement learning transfer-learning |
spellingShingle |
adsorption DFT DFTB functional materials reinforcement learning transfer-learning Lourenço, Maicon Pierre Hostaš, Jiří Bellinger, Colin Tchagang, Alain Salahub, Dennis R. Reinforcement learning for in silico determination of adsorbate: substrate structures |
topic_facet |
adsorption DFT DFTB functional materials reinforcement learning transfer-learning |
description |
Reinforcement learning (RL) methods have helped to define the state of the art in the field of modern artificial intelligence, mostly after the breakthrough involving AlphaGo and the discovery of novel algorithms. In this work, we present a RL method, based on Q-learning, for the structural determination of adsorbate@substrate models in silico, where the minimization of the energy landscape resulting from adsorbate interactions with a substrate is made by actions on states (translations and rotations) chosen from an agent's policy. The proposed RL method is implemented in an early version of the reinforcement learning software for materials design and discovery (RLMaterial), developed in Python3.x. RLMaterial interfaces with deMon2k, DFTB+, ORCA, and Quantum Espresso codes to compute the adsorbate@substrate energies. The RL method was applied for the structural determination of (i) the amino acid glycine and (ii) 2-amino-acetaldehyde, both interacting with a boron nitride (BN) monolayer, (iii) host-guest interactions between phenylboronic acid and β-cyclodextrin and (iv) ammonia on naphthalene. Density functional tight binding calculations were used to build the complex search surfaces with a reasonably low computational cost for systems (i)–(iii) and DFT for system (iv). Artificial neural network and gradient boosting regression techniques were employed to approximate the Q-matrix or Q-table for better decision making (policy) on next actions. Finally, we have developed a transfer-learning protocol within the RL framework that allows learning from one chemical system and transferring the experience to another, as well as from different DFT or DFTB levels. In press: Yes Peer reviewed: Yes NRC publication: Yes |
format |
Article in Journal/Newspaper |
author |
Lourenço, Maicon Pierre Hostaš, Jiří Bellinger, Colin Tchagang, Alain Salahub, Dennis R. |
author_facet |
Lourenço, Maicon Pierre Hostaš, Jiří Bellinger, Colin Tchagang, Alain Salahub, Dennis R. |
author_sort |
Lourenço, Maicon Pierre |
title |
Reinforcement learning for in silico determination of adsorbate: substrate structures |
title_short |
Reinforcement learning for in silico determination of adsorbate: substrate structures |
title_full |
Reinforcement learning for in silico determination of adsorbate: substrate structures |
title_fullStr |
Reinforcement learning for in silico determination of adsorbate: substrate structures |
title_full_unstemmed |
Reinforcement learning for in silico determination of adsorbate: substrate structures |
title_sort |
reinforcement learning for in silico determination of adsorbate: substrate structures |
publisher |
Wiley |
publishDate |
2024 |
url |
https://doi.org/10.1002/jcc.27322 https://nrc-publications.canada.ca/eng/view/object/?id=520f0a4d-de3b-4e83-ba8c-63153ebb5c8e https://nrc-publications.canada.ca/fra/voir/objet/?id=520f0a4d-de3b-4e83-ba8c-63153ebb5c8e |
genre |
Orca |
genre_facet |
Orca |
op_relation |
issn:0192-8651 issn:1096-987X Journal of Computational Chemistry, Publication date: 2024-02-15 doi:10.1002/jcc.27322 |
op_doi |
https://doi.org/10.1002/jcc.27322 |
container_title |
Journal of Computational Chemistry |
container_volume |
45 |
container_issue |
15 |
container_start_page |
1289 |
op_container_end_page |
1302 |
_version_ |
1810470414819786752 |