{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:16:46Z","timestamp":1750220206774,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T00:00:00Z","timestamp":1661731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"U. S. Department of Energy","award":["DE-AC05-00OR22725"],"award-info":[{"award-number":["DE-AC05-00OR22725"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,29]]},"DOI":"10.1145\/3547276.3548635","type":"proceedings-article","created":{"date-parts":[[2023,1,15]],"date-time":"2023-01-15T00:56:17Z","timestamp":1673744177000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Training reinforcement learning models via an adversarial evolutionary algorithm"],"prefix":"10.1145","author":[{"given":"Mark","family":"Coletti","sequence":"first","affiliation":[{"name":"Oak Ridge National Laboratory, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chathika","family":"Gunaratne","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Catherine","family":"Schuman","sequence":"additional","affiliation":[{"name":"University of Tennessee, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Patton","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,1,13]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2022. Gremlin an adversarial evolutionary algorithm that discovers biases or weaknesses in machine learners. https:\/\/github.com\/markcoletti\/gremlin"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"M. Alzantot Y. Sharma A. Elgohary B. Ho M. Srivastava and K. Chang. 2018. Generating Natural Language Adversarial Examples. arxiv:1804.07998\u00a0[cs.CL]","DOI":"10.18653\/v1\/D18-1316"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"A. Angiuli J.P. Fouque and M. Lauri\u00e8re. 2022. Unified reinforcement Q-learning for mean field game and control problems. Mathematics of Control Signals and Systems (2022) 1\u201355.","DOI":"10.1007\/s00498-021-00310-1"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"A.G. Barto R.S. Sutton and C.W. Anderson. 1983. Neuronlike adaptive elements that can solve difficult learning control problems. IEEE transactions on systems man and cybernetics5 (1983) 834\u2013846.","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"e_1_3_2_1_5_1","unstructured":"G. Brockman V. Cheung L. Pettersson J. Schneider J. Schulman J. Tang and W. Zaremba. 2016. OpenAI Gym. arXiv:arXiv:1606.01540"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aquaculture.2021.737838"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3449726.3459573"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3416571"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1162\/106365601750190398"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"P Kofinas AI Dounis and GA Vouros. 2018. Fuzzy Q-Learning for multi-agent decentralized energy management in microgrids. Applied energy 219(2018) 53\u201367.","DOI":"10.1016\/j.apenergy.2018.03.017"},{"volume-title":"2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE, 26\u201332","author":"Nagendra S.","key":"e_1_3_2_1_11_1","unstructured":"S. Nagendra, N. Podila, R. Ugarakhod, and K. George. 2017. Comparison of reinforcement learning algorithms applied to the cart-pole problem. In 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE, 26\u201332."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"R.\u00a0M. Patton A.S. Wu and G.H. Walton. 2003. A Genetic Algorithm Approach to Focused Software Usage Testing. In Software Engineering with Computational Intelligence T.M. Khoshgoftaar (Ed.). Springer US Boston MA 259\u2013286.","DOI":"10.1007\/978-1-4615-0429-0_10"},{"volume-title":"2020 International Joint Conference on Neural Networks (IJCNN). 1\u20138.","author":"Prochazka S.","key":"e_1_3_2_1_13_1","unstructured":"S. Prochazka and R. Neruda. 2020. Black-box Evolutionary Search for Adversarial Examples against Deep Image Classifiers in Non-Targeted Attacks. In 2020 International Joint Conference on Neural Networks (IJCNN). 1\u20138."},{"volume-title":"Programs for Machine Learning","author":"Quinlan R.","key":"e_1_3_2_1_14_1","unstructured":"J.\u00a0R. Quinlan. 1993. C4.5, Programs for Machine Learning. Morgan Kaufmann Publishers."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"A. Sehgal H.M. La S.J. Louis and H. Nguyen. 2019. Deep Reinforcement Learning using Genetic Algorithm for Parameter Optimization. arxiv:1905.04100\u00a0[cs.NE]","DOI":"10.1109\/IRC.2019.00121"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"J. Sun T. Zhang X. Xie L. Ma Y. Zheng K. Chen and Y. Liu. 2020. Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning. In AAAI.","DOI":"10.1609\/aaai.v34i04.6047"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"P. Vidnerov\u00e1 and R. Neruda. 2016. Evolutionary Generation of Adversarial Examples for Deep and Shallow Machine Learning Models. Association for Computing Machinery New York NY USA.","DOI":"10.1145\/2955129.2955178"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"C. Watkins and P. Dayan. 1992. Q-learning. Machine learning 8 3 (1992) 279\u2013292.","DOI":"10.1023\/A:1022676722315"},{"volume-title":"Genetic Algorithm with Multiple Fitness Functions for Generating Adversarial Examples. In 2021 IEEE Congress on Evolutionary Computation (CEC). 1792\u20131799","author":"Wu C.","key":"e_1_3_2_1_19_1","unstructured":"C. Wu, W. Luo, N. Zhou, P. Xu, and T. Zhu. 2021. Genetic Algorithm with Multiple Fitness Functions for Generating Adversarial Examples. In 2021 IEEE Congress on Evolutionary Computation (CEC). 1792\u20131799."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"S.R. Young D.C. Rose J.T. Johnston W.T. Heller T.P. Karnowski T.E. Potok R.M. Patton G. Perdue and J. Miller. 2017. Evolving Deep Networks Using HPC. Association for Computing Machinery New York NY USA.","DOI":"10.1145\/3146347.3146355"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"S.R. Young D.C. Rose T.P. Karnowski S. Lim and R.M. Patton. 2015. Optimizing Deep Learning Hyper-Parameters through an Evolutionary Algorithm. Association for Computing Machinery New York NY USA.","DOI":"10.1145\/2834892.2834896"},{"volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online.","author":"Zou W.","key":"e_1_3_2_1_22_1","unstructured":"W. Zou, S. Huang, J. Xie, X. Dai, and J. Chen. 2020. A Reinforced Generation of Adversarial Examples for Neural Machine Translation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online."}],"event":{"name":"ICPP '22: 51st International Conference on Parallel Processing","acronym":"ICPP '22","location":"Bordeaux France"},"container-title":["Workshop Proceedings of the 51st International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3547276.3548635","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3547276.3548635","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:56Z","timestamp":1750186976000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3547276.3548635"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,29]]},"references-count":22,"alternative-id":["10.1145\/3547276.3548635","10.1145\/3547276"],"URL":"https:\/\/doi.org\/10.1145\/3547276.3548635","relation":{},"subject":[],"published":{"date-parts":[[2022,8,29]]},"assertion":[{"value":"2023-01-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}