{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T05:30:19Z","timestamp":1777959019839,"version":"3.51.4"},"reference-count":39,"publisher":"American Chemical Society (ACS)","issue":"13","license":[{"start":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T00:00:00Z","timestamp":1655337600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T00:00:00Z","timestamp":1655337600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T00:00:00Z","timestamp":1655337600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/100006151","name":"Basic Energy Sciences","doi-asserted-by":"publisher","award":["DE-AC02-06CH11357"],"award-info":[{"award-number":["DE-AC02-06CH11357"]}],"id":[{"id":"10.13039\/100006151","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006151","name":"Basic Energy Sciences","doi-asserted-by":"publisher","award":["DE-SC0022263"],"award-info":[{"award-number":["DE-SC0022263"]}],"id":[{"id":"10.13039\/100006151","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Chem. Inf. Model."],"published-print":{"date-parts":[[2022,7,11]]},"DOI":"10.1021\/acs.jcim.2c00373","type":"journal-article","created":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T21:45:00Z","timestamp":1655415900000},"page":"3169-3179","source":"Crossref","is-referenced-by-count":16,"title":["Exploring Potential Energy Surfaces Using Reinforcement Machine Learning"],"prefix":"10.1021","volume":"62","author":[{"given":"Alexis W.","family":"Mills","sequence":"first","affiliation":[{"name":"Department of Chemistry, University of Washington, Seattle, Washington 98195, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2817-1966","authenticated-orcid":true,"given":"Joshua J.","family":"Goings","sequence":"additional","affiliation":[{"name":"Department of Chemistry, University of Washington, Seattle, Washington 98195, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Beck","sequence":"additional","affiliation":[{"name":"Department of Chemical Engineering, University of Washington, Seattle, Washington 98195, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Yang","sequence":"additional","affiliation":[{"name":"Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, California 94720, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7341-6240","authenticated-orcid":true,"given":"Xiaosong","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Chemistry, University of Washington, Seattle, Washington 98195, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"316","published-online":{"date-parts":[[2022,6,16]]},"reference":[{"key":"ref1\/cit1","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.540030212"},{"key":"ref2\/cit2","doi-asserted-by":"publisher","DOI":"10.1016\/0009-2614(90)87064-X"},{"key":"ref3\/cit3","doi-asserted-by":"publisher","DOI":"10.1021\/j100247a015"},{"key":"ref4\/cit4","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-2860(84)87198-7"},{"key":"ref5\/cit5","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1096-987X(199709)18:12<1473::AID-JCC5>3.0.CO;2-G"},{"key":"ref6\/cit6","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.34"},{"key":"ref7\/cit7","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.0c00971"},{"key":"ref8\/cit8","doi-asserted-by":"publisher","DOI":"10.1093\/imamat\/6.1.76"},{"key":"ref9\/cit9","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-1970-0274029-X"},{"key":"ref10\/cit10","doi-asserted-by":"publisher","DOI":"10.1039\/B108658H"},{"key":"ref11\/cit11","doi-asserted-by":"publisher","DOI":"10.1016\/0009-2614(80)80396-4"},{"key":"ref12\/cit12","doi-asserted-by":"publisher","DOI":"10.1063\/1.449880"},{"key":"ref13\/cit13","doi-asserted-by":"publisher","DOI":"10.1021\/ct050275a"},{"key":"ref14\/cit14","doi-asserted-by":"publisher","DOI":"10.1021\/ct300702v"},{"key":"ref15\/cit15","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-800536-1.00004-6"},{"key":"ref16\/cit16","doi-asserted-by":"publisher","DOI":"10.1039\/C6SC05720A"},{"key":"ref17\/cit17","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.98.146401"},{"key":"ref18\/cit18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1509.02971"},{"key":"ref19\/cit19","first-page":"331","volume":"2","author":"Puterman M. L.","year":"1990","journal-title":"Int. Ser. Oper. Res. Manag. Sci."},{"key":"ref20\/cit20","doi-asserted-by":"publisher","DOI":"10.1177\/0272989X09353194"},{"key":"ref21\/cit21","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(94)00011-O"},{"key":"ref22\/cit22","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref23\/cit23","doi-asserted-by":"publisher","DOI":"10.1021\/jacs.7b12191"},{"key":"ref24\/cit24","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton R. S.","year":"2018"},{"key":"ref25\/cit25","unstructured":"Sutton, R. S.; McAllester, D.; Singh, S.; Mansour, Y. Policy Gradient Methods for Reinforcement Learning with Function Approximation.  Advances in Neural Information Processing Systems 12 (NIPS 1999), 1999, Vol. 12."},{"key":"ref26\/cit26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1302.4971"},{"key":"ref27\/cit27","doi-asserted-by":"publisher","DOI":"10.1115\/1.4051598"},{"key":"ref28\/cit28","unstructured":"Silver, D.; Lever, G.; Heess, N.; Degris, T.; Wierstra, D.; Riedmiller, M. Deterministic Policy Gradient Algorithms.  Proceedings of the 31st International Conference on Machine Learning; Bejing, China, 2014; pp 387\u2013395."},{"key":"ref29\/cit29","doi-asserted-by":"crossref","unstructured":"Peters, J.; Schaal, S. Policy Gradient Methods for Robotics.  2006 IEEE\/RSJ International Conference on Intelligent Robots and Systems, 2006; pp 2219\u20132225.","DOI":"10.1109\/IROS.2006.282564"},{"key":"ref30\/cit30","doi-asserted-by":"crossref","unstructured":"Peters, J.; Vijayakumar, S.; Schaal, S. Natural Actor-Critic.  European Conference on Machine Learning, 2005; pp 280\u2013291.","DOI":"10.1007\/11564096_29"},{"key":"ref31\/cit31","unstructured":"Kakade, S. M. A Natural Policy Gradient.  Advances in Neural Information Processing Systems 14 (NIPS 2001), 2001; Vol.  14."},{"key":"ref32\/cit32","unstructured":"Konda, V. R.; Tsitsiklis, J. N. Actor-Critic Algorithms.  Advances in Neural Information Processing Systems 12 (NIPS 1999), 1999, Vol. 12."},{"key":"ref33\/cit33","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref34\/cit34","doi-asserted-by":"publisher","DOI":"10.2307\/1968873"},{"key":"ref35\/cit35","doi-asserted-by":"publisher","DOI":"10.1063\/1.5012271"},{"key":"ref36\/cit36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref37\/cit37","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2018.11.005"},{"key":"ref38\/cit38","unstructured":"Ng, A. Y.; Harada, D.; Russell, S.Policy Invariance Under Reward Transformations: Theory and Application to Reward Shaping.  Proceedings of the Sixteenth International Conference on Machine Learning, 1999;  Proceedings of the Sixteenth International Conference on Machine Learning; Vol. 99, pp 278\u2013287."},{"key":"ref39\/cit39","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2051436"}],"container-title":["Journal of Chemical Information and Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.2c00373","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.2c00373","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T17:34:26Z","timestamp":1682530466000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/doi\/10.1021\/acs.jcim.2c00373"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,16]]},"references-count":39,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2022,7,11]]}},"alternative-id":["10.1021\/acs.jcim.2c00373"],"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.2c00373","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,16]]}}}