{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T23:58:36Z","timestamp":1785455916589,"version":"3.56.0"},"reference-count":72,"publisher":"American Chemical Society (ACS)","issue":"3","license":[{"start":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T00:00:00Z","timestamp":1775520000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000146","name":"Division of Chemical, Bioengineering, Environmental, and Transport Systems","doi-asserted-by":"publisher","award":["CBET-2143346"],"award-info":[{"award-number":["CBET-2143346"]}],"id":[{"id":"10.13039\/100000146","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000146","name":"Division of Chemical, Bioengineering, Environmental, and Transport Systems","doi-asserted-by":"publisher","award":["CBET-2347040"],"award-info":[{"award-number":["CBET-2347040"]}],"id":[{"id":"10.13039\/100000146","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008109","name":"University of Notre Dame","doi-asserted-by":"publisher","award":["NA"],"award-info":[{"award-number":["NA"]}],"id":[{"id":"10.13039\/100008109","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6,17]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Efficient data selection is critical in domains where data acquisition is expensive and time-consuming, such as material science. In this work, we introduce a novel active learning framework that integrates proximal policy optimization (PPO) with Gaussian process regression (GPR) to strategically select informative data points and thereby enhance predictive modeling. Leveraging the inherent stability and sample efficiency of PPO, achieved through a clipped surrogate objective, the framework guides data acquisition via a custom-designed Gymnasium environment tailored for GPR. In this environment, the PPO agent dynamically chooses data points based on their potential to improve the GPR\u2019s performance, as measured by the R2 score, while preventing redundancy through an action masking mechanism. We apply the proposed methodology to predict the selectivity of methane (CH4) over higher alkanes in metal\u2013organic frameworks (MOFs), focusing on CuBTC and IRMOF-1. The framework is evaluated using both ternary and quaternary gas mixtures, where the performance of the GPR is assessed through metrics such as R2, mean absolute error (MAE), and root mean squared error (RMSE). Across CuBTC and IRMOF-1 in ternary and quaternary hydrocarbon mixtures, PPO-guided acquisition achieves 77\u201386% data savings relative to full GCMC grids, typically querying only \u223c14\u201323% of the candidate pool while the clipped-update PPO policy converges stably by focusing selections in the pressure\u2013temperature\u2013composition regions where selectivity changes most rapidly. This work shows the potential of combining advanced reinforcement learning techniques with regression models to accelerate material discovery and optimize gas separation processes.<\/jats:p>","DOI":"10.1021\/acsengineeringau.5c00122","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T12:00:38Z","timestamp":1775563238000},"page":"446-462","source":"Crossref","is-referenced-by-count":0,"title":["PPO-GPR: A Custom Proximal Policy Optimization Tool\nfor Active Reinforcement Learning"],"prefix":"10.1021","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2744-339X","authenticated-orcid":true,"given":"Etinosa","family":"Osaro","sequence":"first","affiliation":[{"name":"University of Notre Dame , , , ,","place":["Notre Dame, Indiana, United States, 46556"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5316-9692","authenticated-orcid":true,"given":"Yamil J.","family":"Colo\u0301n","sequence":"additional","affiliation":[{"name":"University of Notre Dame , , , ,","place":["Notre Dame, Indiana, United States, 46556"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,4,7]]},"reference":[{"key":"2026073019122679300_cit1","doi-asserted-by":"publisher","DOI":"10.1002\/adfm.202000238","article-title":"Pore Chemistry\nof Metal\u2013Organic Frameworks","volume":"30","author":"Ji","year":"2020","journal-title":"Adv. Funct.\nMater."},{"key":"2026073019122679300_cit2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1230444","article-title":"The Chemistry and\nApplications of Metal-Organic Frameworks","volume":"341","author":"Furukawa","year":"2013","journal-title":"Science"},{"key":"2026073019122679300_cit3","first-page":"575","article-title":"Progress in Advanced\nCharacterization of MOFs","volume-title":"The Chemistry\nof Metal-Organic Frameworks: Synthesis, Characterization, and Applications","author":"Kaskel","year":"2016"},{"key":"2026073019122679300_cit4","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1039\/b200393g","article-title":"Metal-organic\nframeworks","volume":"32","author":"James","year":"2003","journal-title":"Chem. Soc. Rev."},{"key":"2026073019122679300_cit5","doi-asserted-by":"publisher","first-page":"1504","DOI":"10.1021\/jacsau.2c00376","article-title":"Metal-Organic\nFrameworks and Covalent Organic Frameworks: Emerging Advances and\nApplications","volume":"2","author":"Jones","year":"2022","journal-title":"JACS Au"},{"key":"2026073019122679300_cit6","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1016\/j.electacta.2013.10.190","article-title":"Hydrogen storage\nin metal-organic frameworks: A review","volume":"128","author":"Langmi","year":"2014","journal-title":"Electrochim.\nActa"},{"key":"2026073019122679300_cit7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s42004-019-0184-6","article-title":"Metal-organic framework\nfunctionalization and design strategies for advanced electrochemical\nenergy storage devices","volume":"2","author":"Baumann","year":"2019","journal-title":"Commun. Chem."},{"key":"2026073019122679300_cit8","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.abo6849","article-title":"A scalable solid-state\nnanoporous network with atomic-level interaction design for carbon\ndioxide capture","volume":"8","author":"Mao","year":"2022","journal-title":"Sci. Adv."},{"key":"2026073019122679300_cit9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ccr.2023.215111","article-title":"Designed metal-organic\nframeworks with potential for multi-component hydrocarbon separation","volume":"484","author":"Wang","year":"2023","journal-title":"Coord. Chem. Rev."},{"key":"2026073019122679300_cit10","doi-asserted-by":"publisher","DOI":"10.1016\/j.matt.2025.102140","article-title":"CoRE MOF\nDB: A curated\nexperimental metal-organic framework database with machine-learned\nproperties for integrated material-process screening","volume":"8","author":"Zhao","year":"2025","journal-title":"Matter"},{"key":"2026073019122679300_cit11","doi-asserted-by":"publisher","first-page":"5985","DOI":"10.1021\/acs.jced.9b00835","article-title":"Advances, Updates, and\nAnalytics for the Computation-Ready, Experimental Metal\u2013Organic\nFramework Database: CoRE MOF 2019","volume":"64","author":"Chung","year":"2019","journal-title":"J. Chem.\nEng. Data"},{"key":"2026073019122679300_cit12","doi-asserted-by":"publisher","first-page":"5735","DOI":"10.1039\/C4CS00070F","article-title":"High-throughput computational screening of metal-organic\nframeworks","volume":"43","author":"Colo\u0301n","year":"2014","journal-title":"Chem. Soc. Rev."},{"key":"2026073019122679300_cit13","doi-asserted-by":"publisher","DOI":"10.1063\/5.0295283","article-title":"Intelligent\nscreening of porous materials: A review\nof active-learning approaches in MOF research","volume":"6","author":"Osaro","year":"2025","journal-title":"Chem. Phys. Rev."},{"key":"2026073019122679300_cit14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cej.2022.136651","article-title":"Interpretable\nmachine learning for\naccelerating the discovery of metal-organic frameworks for ethane\/ethylene\nseparation","volume":"444","author":"Wang","year":"2022","journal-title":"Chem. Eng. J."},{"key":"2026073019122679300_cit15","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-019-0153-8","article-title":"Active learning in\nmaterials science with emphasis on adaptive sampling using uncertainties\nfor targeted design","volume":"5","author":"Lookman","year":"2019","journal-title":"NPJ. Comput. Mater."},{"key":"2026073019122679300_cit16","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1613\/jair.295","article-title":"Active Learning with Statistical\nModels","volume":"4","author":"Cohn","year":"1996","journal-title":"J. Artif. Intell. Res."},{"key":"2026073019122679300_cit17","doi-asserted-by":"publisher","DOI":"10.1063\/1.5005095","article-title":"Machine learning of molecular properties:\nLocality and active learning","volume":"148","author":"Gubaev","year":"2018","journal-title":"J. Chem. Phys."},{"key":"2026073019122679300_cit18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3472291","article-title":"A Survey of Deep Active\nLearning","volume":"54","author":"Ren","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"2026073019122679300_cit19","doi-asserted-by":"publisher","first-page":"13009","DOI":"10.1021\/acs.iecr.3c01589","article-title":"Active Learning for Adsorption Simulations:\nEvaluation, Criteria Analysis, and Recommendations for Metal\u2013Organic\nFrameworks","volume":"62","author":"Osaro","year":"2023","journal-title":"Ind. Eng. Chem. Res."},{"key":"2026073019122679300_cit20","doi-asserted-by":"publisher","first-page":"1506","DOI":"10.1039\/D3DD00106G","article-title":"Active\nlearning for efficient navigation\nof multi-component gas adsorption landscapes in a MOF","volume":"2","author":"Mukherjee","year":"2023","journal-title":"Digital Discovery"},{"key":"2026073019122679300_cit21","doi-asserted-by":"publisher","first-page":"17671","DOI":"10.1039\/D4SC02156H","article-title":"Active learning of alchemical adsorption simulations;\ntowards a universal adsorption model","volume":"15","author":"Osaro","year":"2024","journal-title":"Chem.\nSci."},{"key":"2026073019122679300_cit22","doi-asserted-by":"publisher","first-page":"9877","DOI":"10.1021\/acs.jpcc.5c00922","article-title":"Harmonizing\nAdsorption and Diffusion\nin Active Learning Campaigns of Gas Separations in a MOF","volume":"129","author":"Osaro","year":"2025","journal-title":"J. Phys. Chem. C"},{"key":"2026073019122679300_cit23","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1038\/s43246-025-00933-w","article-title":"Multi-method\nmaterial selection for\nadsorption using Bayesian approaches","volume":"6","author":"Osaro","year":"2025","journal-title":"Commun.\nMater."},{"key":"2026073019122679300_cit24","doi-asserted-by":"publisher","first-page":"1937","DOI":"10.1039\/D3DD00117B","article-title":"Multi-fidelity Bayesian\noptimization of covalent organic frameworks for xenon\/krypton separations","volume":"2","author":"Gantzler","year":"2023","journal-title":"Digital Discovery"},{"key":"2026073019122679300_cit25","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2024.117373","article-title":"Active learning inspired multi-fidelity\nprobabilistic modelling of geomaterial property","volume":"432","author":"He","year":"2024","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"2026073019122679300_cit26","unstructured":"Hernandez-Garcia, A.; Saxena, N.; Jain, M.; Liu, C.-H.; Bengio, Y.\n          Multi-Fidelity Active Learning\nwith GFlowNets. 2024."},{"key":"2026073019122679300_cit27","doi-asserted-by":"publisher","DOI":"10.1093\/oxfmat\/itac006","article-title":"Benchmarking\nactive learning strategies for materials optimization and discovery","volume":"2","author":"Wang","year":"2022","journal-title":"Oxford Open Mater. Sci."},{"key":"2026073019122679300_cit28","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-19597-w","article-title":"On-the-fly closed-loop materials discovery\nvia Bayesian active learning","volume":"11","author":"Kusne","year":"2020","journal-title":"Nat. Commun."},{"key":"2026073019122679300_cit29","doi-asserted-by":"publisher","first-page":"10073","DOI":"10.1021\/acs.chemrev.1c00022","article-title":"Gaussian Process Regression\nfor Materials and Molecules","volume":"121","author":"Deringer","year":"2021","journal-title":"Chem. Rev."},{"key":"2026073019122679300_cit30","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/978-3-540-28650-9_4","article-title":"Gaussian Processes\nin machine learning","volume-title":"Lecture Notes in Computer\nScience","author":"Rasmussen","year":"2004"},{"key":"2026073019122679300_cit31","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3206.001.0001","volume-title":"Gaussian Processes\nfor Machine Learning","author":"Rasmussen","year":"2005"},{"key":"2026073019122679300_cit32","unstructured":"Hensman, J.; Fusi, N.; Lawrence, N. D.\n          Gaussian Processes\nfor Big\nData\n          2013\n          https:\/\/arxiv.org\/pdf\/1309.6835."},{"key":"2026073019122679300_cit33","unstructured":"Li, Y.\n          \n          Deep Reinforcement\nLearning: An Overview\n          2017\n          https:\/\/arxiv.org\/abs\/1701.07274."},{"key":"2026073019122679300_cit34","doi-asserted-by":"publisher","first-page":"1433","DOI":"10.1021\/acsmaterialslett.1c00390","article-title":"Deep Reinforcement\nLearning for Digital Materials Design","volume":"3","author":"Sui","year":"2021","journal-title":"ACS Mater.\nLett."},{"key":"2026073019122679300_cit35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-1-4615-3618-5_1","article-title":"Introduction:\nThe Challenge of Reinforcement Learning","volume-title":"Reinforcement Learning","author":"Sutton","year":"1992"},{"key":"2026073019122679300_cit36","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement\nLearning: A Survey","volume":"4","author":"Kaelbling","year":"1996","journal-title":"J. Artif. Intell. Res."},{"key":"2026073019122679300_cit37","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s10994-013-5340-0","article-title":"A reinforcement learning\napproach to autonomous decision-making in smart electricity markets","volume":"92","author":"Peters","year":"2013","journal-title":"Mach. Learn."},{"key":"2026073019122679300_cit38","doi-asserted-by":"publisher","DOI":"10.1002\/aic.18611","article-title":"Optimizing the prediction of adsorption\nin metal\u2013organic\nframeworks leveraging Q-learning","volume":"70","author":"Osaro","year":"2024","journal-title":"AIChE J."},{"key":"2026073019122679300_cit39","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1039\/D4DD00010B","article-title":"Inverse design\nof metal\u2013organic frameworks for direct air capture of CO 2via deep reinforcement learning","volume":"3","author":"Park","year":"2024","journal-title":"Digital Discovery"},{"key":"2026073019122679300_cit40","unstructured":"Zhuang, Z.; Lei, K.; Liu, J.; Wang, D.; Guo, Y.\n          Behavior Proximal Policy Optimization. 2023."},{"key":"2026073019122679300_cit41","doi-asserted-by":"publisher","first-page":"4600","DOI":"10.1109\/TSMC.2021.3098451","article-title":"Proximal Policy Optimization\nWith Policy Feedback","volume":"52","author":"Gu","year":"2022","journal-title":"IEEE Trans. Syst. Man\nCybern. Syst."},{"key":"2026073019122679300_cit42","unstructured":"Schulman, J.; Wolski, F.; Dhariwal, P.; Radford, A.; Klimov, O.\n          Proximal Policy\nOptimization Algorithms. 2017."},{"key":"2026073019122679300_cit43","unstructured":"Kostrikov, I.; Nair, A.; Levine, S.\n          Offline Reinforcement\nLearning\nwith Implicit Q-Learning\n          2021\n          https:\/\/arxiv.org\/abs\/2110.06169."},{"key":"2026073019122679300_cit44","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1007\/978-3-319-70093-9_50","article-title":"Deep Reinforcement\nLearning: From\nQ-Learning to Deep Q-Learning","volume-title":"Neural Information\nProcessing","author":"Tan","year":"2017"},{"key":"2026073019122679300_cit45","doi-asserted-by":"publisher","first-page":"133653","DOI":"10.1109\/ACCESS.2019.2941229","article-title":"Q-Learning Algorithms: A Comprehensive\nClassification and Applications","volume":"7","author":"Jang","year":"2019","journal-title":"IEEE Access"},{"key":"2026073019122679300_cit46","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1146\/annurev-statistics-031219-041220","article-title":"Q-Learning: Theory\nand Applications","volume":"7","author":"Clifton","year":"2020","journal-title":"Annu.\nRev. Stat. Appl."},{"key":"2026073019122679300_cit47","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Mach. Learn."},{"key":"2026073019122679300_cit48","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1007\/978-981-19-7784-8_10","article-title":"Deep Reinforcement\nLearning","volume-title":"Reinforcement Learning for Sequential\nDecision and Optimal Control","author":"Li","year":"2023"},{"key":"2026073019122679300_cit49","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e30697","article-title":"Deep deterministic policy\ngradient algorithm: A systematic review","volume":"10","author":"Sumiea","year":"2024","journal-title":"Heliyon"},{"key":"2026073019122679300_cit50","doi-asserted-by":"publisher","first-page":"4213","DOI":"10.1609\/aaai.v33i01.33014213","article-title":"Robust Multi-Agent Reinforcement Learning via\nMinimax Deep Deterministic Policy Gradient","volume":"33","author":"Li","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"2026073019122679300_cit51","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/CAIBDA53561.2021.00025","article-title":"Reinforcement\nLearning with Deep Deterministic Policy Gradient","volume-title":"2021 International Conference on Artificial Intelligence,\nBig Data and Algorithms (CAIBDA)","author":"Tan","year":"2021"},{"key":"2026073019122679300_cit52","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1016\/j.ins.2022.07.111","article-title":"Proximal policy\noptimization via enhanced exploration efficiency","volume":"609","author":"Zhang","year":"2022","journal-title":"Inf. Sci."},{"key":"2026073019122679300_cit53","unstructured":"Schulman, J.; Wolski, F.; Dhariwal, P.; Radford, A.; Klimov, O.\n          Proximal Policy\nOptimization Algorithms\n          2017\n          https:\/\/arxiv.org\/abs\/1707.06347."},{"key":"2026073019122679300_cit54","doi-asserted-by":"publisher","first-page":"1125","DOI":"10.1109\/TCCN.2019.2952909","article-title":"A Deep Actor-Critic Reinforcement\nLearning Framework for Dynamic Multichannel Access","volume":"5","author":"Zhong","year":"2019","journal-title":"IEEE Trans. Cogn. Commun. Netw."},{"key":"2026073019122679300_cit55","unstructured":"Gruslys, A.; Dabney, W.; Azar, M. G.; et al.\n          The\nReactor: A fast and sample-efficient Actor-Critic agent for Reinforcement\nLearning\n          2017\n          https:\/\/arxiv.org\/abs\/1704.04651."},{"key":"2026073019122679300_cit56","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.conb.2020.08.005","article-title":"Actor-critic reinforcement\nlearning in the songbird","volume":"65","author":"Chen","year":"2020","journal-title":"Curr. Opin. Neurobiol."},{"key":"2026073019122679300_cit57","doi-asserted-by":"publisher","first-page":"6217","DOI":"10.1109\/LRA.2020.3011351","article-title":"Actor-Critic Reinforcement\nLearning for Control With Stability Guarantee","volume":"5","author":"Han","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"2026073019122679300_cit58","doi-asserted-by":"publisher","first-page":"1291","DOI":"10.1109\/TSMCC.2012.2218595","article-title":"A Survey of\nActor-Critic\nReinforcement Learning: Standard and Natural Policy Gradients","volume":"42","author":"Grondman","year":"2012","journal-title":"IEEE Trans. Syst, Man, Cybern."},{"key":"2026073019122679300_cit59","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1080\/09540099108946587","article-title":"Function Optimization\nusing Connectionist Reinforcement Learning\nAlgorithms","volume":"3","author":"WILLIAMS","year":"1991","journal-title":"Connect. Sci."},{"key":"2026073019122679300_cit60","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1023\/A:1022672621406","article-title":"Simple\nstatistical gradient-following algorithms for connectionist reinforcement\nlearning","volume":"8","author":"Williams","year":"1992","journal-title":"Mach. Learn."},{"key":"2026073019122679300_cit61","doi-asserted-by":"publisher","first-page":"10887","DOI":"10.1609\/aaai.v35i12.17300","article-title":"Sample Efficient Reinforcement\nLearning with REINFORCE","volume":"35","author":"Zhang","year":"2021","journal-title":"Proc. AAAI Conf. Artif.\nIntell."},{"key":"2026073019122679300_cit62","unstructured":"Brockman, G.; Cheung, V.; Pettersson, L.; et al.\n          OpenAI\nGym\n          2016\n          https:\/\/arxiv.org\/abs\/1606.01540."},{"key":"2026073019122679300_cit63","unstructured":"Towers, M.; Kwiatkowski, A.; Terry, J.; et al.\n          Gymnasium: A Standard\nInterface for Reinforcement Learning Environments\n          2024\n          https:\/\/arxiv.org\/abs\/2407.17032."},{"key":"2026073019122679300_cit64","first-page":"1","article-title":"Stable-Baselines3: Reliable\nReinforcement Learning Implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"J. Mach.\nLearn. Res."},{"key":"2026073019122679300_cit65","doi-asserted-by":"publisher","first-page":"10024","DOI":"10.1021\/ja00051a040","article-title":"UFF, a\nFull Periodic Table Force Field for Molecular Mechanics and Molecular\nDynamics Simulations","volume":"114","author":"Rappe\u0301","year":"1992","journal-title":"J. Am. Chem. Soc."},{"key":"2026073019122679300_cit66","doi-asserted-by":"publisher","first-page":"2569","DOI":"10.1021\/jp972543+","article-title":"Transferable Potentials\nfor Phase Equilibria. 1. United-Atom\nDescription of n-Alkanes","volume":"102","author":"Martin","year":"1998","journal-title":"J. Phys. Chem. B"},{"key":"2026073019122679300_cit67","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1080\/08927022.2015.1010082","article-title":"RASPA: Molecular\nsimulation software for adsorption and diffusion in flexible nanoporous\nmaterials","volume":"42","author":"Dubbeldam","year":"2016","journal-title":"Mol. Simul."},{"key":"2026073019122679300_cit68","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-95246-6","article-title":"Towards estimation of\nCO2 adsorption on highly porous MOF-based adsorbents using gaussian\nprocess regression approach","volume":"11","author":"Gheytanzadeh","year":"2021","journal-title":"Sci. Rep."},{"key":"2026073019122679300_cit69","doi-asserted-by":"publisher","DOI":"10.3390\/app12104946","article-title":"Gaussian Processes\nfor Signal Processing and Representation\nin Control Engineering","volume":"12","author":"Dudek","year":"2022","journal-title":"Appl. Sci."},{"key":"2026073019122679300_cit70","first-page":"2104","article-title":"Gaussian process kernels for\npattern discovery and extrapolation","volume-title":"30th\nInternational Conference on Machine Learning, ICML 2013","author":"Wilson","year":"2013"},{"key":"2026073019122679300_cit71","unstructured":"Melkumyan, A.; Ramos, F.\n          Multi-kernel Gaussian Processes, IJCAI International Joint Conference on Artificial Intelligence, 2011; pp 1408\u2013141310.5591\/978-1-57735-516-8\/IJCAI11-238."},{"key":"2026073019122679300_cit72","first-page":"8185","article-title":"Combining Latent\nSpace and Structured Kernels for Bayesian Optimization over Combinatorial\nSpaces","volume-title":"Advances in Neural Information\nProcessing Systems","author":"Deshwal","year":"2021"}],"container-title":["ACS Engineering Au"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acsengineeringau.5c00122","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/aeacb3\/article-pdf\/6\/3\/446\/66258334\/acsengineeringau.5c00122.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/aeacb3\/article-pdf\/6\/3\/446\/66258334\/acsengineeringau.5c00122.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T23:12:35Z","timestamp":1785453155000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/aeacb3\/article\/6\/3\/446\/5232576\/PPO-GPR-A-Custom-Proximal-Policy-Optimization-Tool"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,7]]},"references-count":72,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,4,7]]},"published-print":{"date-parts":[[2026,6,17]]}},"URL":"https:\/\/doi.org\/10.1021\/acsengineeringau.5c00122","relation":{},"ISSN":["2694-2488"],"issn-type":[{"value":"2694-2488","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,7]]}}}