{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T13:23:37Z","timestamp":1777555417998,"version":"3.51.4"},"reference-count":49,"publisher":"SAGE Publications","issue":"2","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Data Science"],"published-print":{"date-parts":[[2024,11,25]]},"abstract":"<jats:p>Stable states in complex systems correspond to local minima on the associated potential energy surface. Transitions between these local minima govern the dynamics of such systems. Precisely determining the transition pathways in complex and high-dimensional systems is challenging because these transitions are rare events, and isolating the relevant species in experiments is difficult. Most of the time, the system remains near a local minimum, with rare, large fluctuations leading to transitions between minima. The probability of such transitions decreases exponentially with the height of the energy barrier, making the system\u2019s dynamics highly sensitive to the calculated energy barriers. This work aims to formulate the problem of finding the minimum energy barrier between two stable states in the system\u2019s state space as a cost-minimization problem. It is proposed to solve this problem using reinforcement learning algorithms. The exploratory nature of reinforcement learning agents enables efficient sampling and determination of the minimum energy barrier for transitions.<\/jats:p>","DOI":"10.3233\/ds-240063","type":"journal-article","created":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T11:04:50Z","timestamp":1729595090000},"page":"73-92","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":1,"title":["Estimating reaction barriers with deep reinforcement learning"],"prefix":"10.1177","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0705-7768","authenticated-orcid":false,"given":"Adittya","family":"Pal","sequence":"first","affiliation":[{"name":"Institut for Matematik og Datalogi, Syddansk Universitet, Campusvej 55, 5230 Odense M, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"ref001","unstructured":"Y.\u00a0Bai, E.\u00a0Yang, B.\u00a0Han, Y.\u00a0Yang, J.\u00a0Li, Y.\u00a0Mao, G.\u00a0Niu and T.\u00a0Liu, Understanding and improving early stopping for learning with noisy labels, in: Advances in Neural Information Processing Systems, M.\u00a0Ranzato, A.\u00a0Beygelzimer, Y.\u00a0Dauphin, P.S.\u00a0Liang and J.W.\u00a0Vaughan, eds, Vol.\u00a034, Curran Associates, Inc., 2021, pp.\u00a024392\u201324403, https:\/\/dl.acm.org\/doi\/10.5555\/3540261.3542128."},{"key":"ref002","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jpclett.3c02771"},{"key":"ref003","unstructured":"C.\u00a0Beeler, S.G.\u00a0Subramanian, K.\u00a0Sprague, C.\u00a0Bellinger, M.\u00a0Crowley and I.\u00a0Tamblyn, Demonstrating ChemGymRL: An interactive framework for reinforcement learning for digital chemistry, in: AI for Accelerated Materials Design \u2013 NeurIPS 2023 Workshop, 2023, https:\/\/openreview.net\/forum?id=cSz69rFRvS."},{"key":"ref004","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.104.064128"},{"key":"ref005","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1995.7.1.108"},{"key":"ref006","doi-asserted-by":"publisher","DOI":"10.1002\/adts.202000237"},{"key":"ref007","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11645"},{"key":"ref008","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-36823-3"},{"key":"ref009","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-023-00563-7"},{"key":"ref010","doi-asserted-by":"publisher","DOI":"10.1063\/1.2720838"},{"key":"ref011","unstructured":"S.\u00a0Fujimoto, H.\u00a0van Hoof and D.\u00a0Meger, Addressing Function Approximation Error in Actor-Critic Methods, 2018, https:\/\/arxiv.org\/abs\/1802.09477."},{"key":"ref012","doi-asserted-by":"publisher","DOI":"10.1063\/1.3156312"},{"key":"ref013","doi-asserted-by":"publisher","DOI":"10.1039\/D2DD00047D"},{"key":"ref014","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2023.133955"},{"key":"ref015","unstructured":"T.\u00a0Haarnoja, A.\u00a0Zhou, P.\u00a0Abbeel and S.\u00a0Levine, Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor, 2018, https:\/\/arxiv.org\/abs\/1801.01290."},{"key":"ref016","unstructured":"T.\u00a0Haarnoja, A.\u00a0Zhou, K.\u00a0Hartikainen, G.\u00a0Tucker, S.\u00a0Ha, J.\u00a0Tan, V.\u00a0Kumar, H.\u00a0Zhu, A.\u00a0Gupta, P.\u00a0Abbeel and S.\u00a0Levine, Soft Actor-Critic Algorithms and Applications, 2019, https:\/\/arxiv.org\/abs\/1812.05905."},{"key":"ref017","doi-asserted-by":"publisher","DOI":"10.1063\/5.0112856"},{"key":"ref018","doi-asserted-by":"publisher","DOI":"10.1063\/1.1329672"},{"key":"ref019","unstructured":"L.\u00a0Holdijk, Y.\u00a0Du, F.\u00a0Hooft, P.\u00a0Jaini, B.\u00a0Ensing and M.\u00a0Welling, Stochastic Optimal Control for Collective Variable Free Sampling of Molecular Transition Paths, 2023, https:\/\/arxiv.org\/abs\/2207.02149."},{"key":"ref020","doi-asserted-by":"publisher","DOI":"10.1039\/D1SC01206A"},{"key":"ref021","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.24720"},{"key":"ref022","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-023-00428-z"},{"key":"ref023","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref024","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2020.107027"},{"key":"ref025","doi-asserted-by":"publisher","DOI":"10.1063\/1.4986787"},{"key":"ref026","doi-asserted-by":"publisher","DOI":"10.1021\/jacs.1c08794"},{"key":"ref027","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-50531-6"},{"key":"ref028","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.3c02070"},{"key":"ref029","doi-asserted-by":"publisher","DOI":"10.1162\/artl.1993.1.1_2.135"},{"key":"ref030","doi-asserted-by":"publisher","DOI":"10.1063\/5.0055094"},{"key":"ref031","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2016.7849365"},{"key":"ref032","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.2c00373"},{"key":"ref033","doi-asserted-by":"publisher","DOI":"10.1007\/BF00547608"},{"key":"ref034","unstructured":"P.\u00a0Nakkiran, G.\u00a0Kaplun, Y.\u00a0Bansal, T.\u00a0Yang, B.\u00a0Barak and I.\u00a0Sutskever, Deep double descent: Where bigger models and more data hurt, in: International Conference on Learning Representations, 2020, https:\/\/openreview.net\/forum?id=B1g5sA4twr."},{"key":"ref035","unstructured":"D.\u00a0Osmankovi\u0107 and S.\u00a0Konjicija, Implementation of Q \u2014 learning algorithm for solving maze problem, in: 2011 Proceedings of the 34th International Convention MIPRO, 2011, https:\/\/ieeexplore.ieee.org\/document\/5967320, pp.\u00a01619\u20131622."},{"key":"ref036","unstructured":"E.\u00a0Parisotto and R.\u00a0Salakhutdinov, Neural Map: Structured Memory for Deep Reinforcement Learning, 2017, https:\/\/arxiv.org\/abs\/1702.08360."},{"key":"ref037","unstructured":"G.M.\u00a0Rotskoff, A.R.\u00a0Mitchell and E.\u00a0Vanden-Eijnden, Active importance sampling for variational objectives dominated by rare events: Consequences for optimization and generalization, in: Proceedings of the 2nd Mathematical and Scientific Machine Learning Conference, J.\u00a0Bruna, J.\u00a0Hesthaven and L.\u00a0Zdeborova, eds, Proceedings of Machine Learning Research, Vol.\u00a0145, PMLR, 2022, pp.\u00a0757\u2013780, https:\/\/proceedings.mlr.press\/v145\/rotskoff22a.html."},{"key":"ref038","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103535"},{"key":"ref039","unstructured":"R.S.\u00a0Sutton and A.G.\u00a0Barto, Reinforcement Learning: An Introduction, a Bradford Book, MIT Press, 1998, https:\/\/books.google.dk\/books?id=CAFR6IBF4xYC. ISBN 9780262193986."},{"key":"ref040","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.8127026"},{"key":"ref041","unstructured":"G.\u00a0Veviurko, W.\u00a0Bohmer\u0308 and M.\u00a0de\u00a0Weerdt, 2024, To the Max: Reinventing Reward in Reinforcement Learning, https:\/\/arxiv.org\/abs\/2402.01361."},{"key":"ref042","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.1c00809"},{"key":"ref043","unstructured":"B.\u00a0Wander, M.\u00a0Shuaibi, J.R.\u00a0Kitchin, Z.W.\u00a0Ulissi and C.L.\u00a0Zitnick, CatTSunami: Accelerating Transition State Energy Calculations with Pre-trained Graph Neural Networks, 2024, https:\/\/arxiv.org\/abs\/2405.02078."},{"key":"ref044","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-022-00369-z"},{"key":"ref045","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.920231"},{"key":"ref046","doi-asserted-by":"publisher","DOI":"10.1039\/D2RE00406B"},{"key":"ref047","doi-asserted-by":"publisher","DOI":"10.1039\/D0CP06184K"},{"key":"ref048","unstructured":"X.\u00a0Zhang, Actor-Critic Algorithm for High-dimensional Partial Differential Equations, 2020, https:\/\/arxiv.org\/abs\/2010.03647."},{"key":"ref049","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.7b00492"}],"container-title":["Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/DS-240063","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/DS-240063","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/DS-240063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T18:10:11Z","timestamp":1777399811000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/DS-240063"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"references-count":49,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,11,25]]}},"alternative-id":["10.3233\/DS-240063"],"URL":"https:\/\/doi.org\/10.3233\/ds-240063","relation":{},"ISSN":["2451-8484","2451-8492"],"issn-type":[{"value":"2451-8484","type":"print"},{"value":"2451-8492","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]}}}