{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T15:38:03Z","timestamp":1778600283595,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,14]],"date-time":"2024-07-14T00:00:00Z","timestamp":1720915200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,14]]},"DOI":"10.1145\/3638529.3653992","type":"proceedings-article","created":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T16:33:04Z","timestamp":1720456384000},"page":"1479-1487","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Emergent Behavior in Evolutionary Swarms for Machine Olfaction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6682-5337","authenticated-orcid":false,"given":"Kordel","family":"France","sequence":"first","affiliation":[{"name":"University of Texas at Dallas, Dallas, Texas, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0484-0691","authenticated-orcid":false,"given":"Anirban","family":"Paul","sequence":"additional","affiliation":[{"name":"University of Texas at Dallas, Dallas, Texas, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3726-3934","authenticated-orcid":false,"given":"Ivneet","family":"Banga","sequence":"additional","affiliation":[{"name":"University of Texas at Dallas, Dallas, Texas, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2404-3801","authenticated-orcid":false,"given":"Shalini","family":"Prasad","sequence":"additional","affiliation":[{"name":"University of Texas at Dallas, Dallas, Texas, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,7,14]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Proceedings of the Twenty-First International Conference on Machine Learning (Banff","author":"Abbeel Pieter","unstructured":"Pieter Abbeel and Andrew Y. Ng. 2004. Apprenticeship Learning via Inverse Reinforcement Learning. In Proceedings of the Twenty-First International Conference on Machine Learning (Banff, Alberta, Canada) (ICML '04). Association for Computing Machinery, New York, NY, USA, 1."},{"key":"e_1_3_2_2_2_1","volume-title":"CoRR abs\/1606.01540","author":"Brockman Greg","year":"2016","unstructured":"Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, John Schulman, Jie Tang, and Wojciech Zaremba. 2016. OpenAI Gym. CoRR abs\/1606.01540 (2016). arXiv:1606.01540 http:\/\/arxiv.org\/abs\/1606.01540"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10827-021-00798-1"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-30164-8_22"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/9780470512517"},{"key":"e_1_3_2_2_6_1","unstructured":"Jonas Eschmann Dario Albani and Giuseppe Loianno. 2023. Learning to Fly in Seconds. arXiv:2311.13081 [cs.RO]"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/SCIS-ISIS.2012.6505078"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583131.3590376"},{"key":"e_1_3_2_2_9_1","unstructured":"Justin Fu Aviral Kumar Ofir Nachum George Tucker and Sergey Levine. 2020. D4RL: Datasets for Deep Data-Driven Reinforcement Learning. arXiv:2004.07219 [cs.LG]"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"crossref","unstructured":"Todd Hester Matej Vecerik Olivier Pietquin Marc Lanctot Tom Schaul Bilal Piot Dan Horgan John Quan Andrew Sendonaris Ian Osband Gabriel Dulac-Arnold John Agapiou Joel Z. Leibo and Audrunas Gruslys. 2018. Deep Q-Learning from Demonstrations. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence (New Orleans Louisiana USA) (AAAI'18\/IAAI'18\/EAAI'18). AAAI Press.","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"e_1_3_2_2_11_1","first-page":"1","article-title":"Deep reinforcement learning for swarm systems","volume":"20","author":"H\u00fcttenrauch Maximilian","year":"2019","unstructured":"Maximilian H\u00fcttenrauch, Adrian \u0160o\u0161i\u0107, and Gerhard Neumann. 2019. Deep reinforcement learning for swarm systems. J. Mach. Learn. Res. 20, 1 (jan 2019), 1966--1996.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1995.488968"},{"key":"e_1_3_2_2_13_1","unstructured":"Theta Diagnostics LLC. 2024. Alchemy Explainable Machine Learning Framework. https:\/\/thetadx.ai\/alchemy"},{"key":"e_1_3_2_2_14_1","volume-title":"Learning from an unknown environment. Ph. D. Dissertation. EECS Department","author":"Muthukumar Vidya","unstructured":"Vidya Muthukumar. 2020. Learning from an unknown environment. Ph. D. Dissertation. EECS Department, University of California, Berkeley."},{"key":"e_1_3_2_2_15_1","unstructured":"Long Ouyang Jeff Wu Xu Jiang Diogo Almeida Carroll L. Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray John Schulman Jacob Hilton Fraser Kelton Luke Miller Maddie Simens Amanda Askell Peter Welinder Paul Christiano Jan Leike and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. arXiv:2203.02155 [cs.CL]"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2020.100718"},{"key":"e_1_3_2_2_17_1","unstructured":"Edoardo M. Ponti Alessandro Sordoni Yoshua Bengio and Siva Reddy. 2022. Combining Modular Skills in Multitask Learning. arXiv:2202.13914 [cs.LG]"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2107431118"},{"key":"e_1_3_2_2_19_1","volume-title":"Proceedings of the 32nd International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"1897","author":"Schulman John","year":"2015","unstructured":"John Schulman, Sergey Levine, Pieter Abbeel, Michael Jordan, and Philipp Moritz. 2015. Trust Region Policy Optimization. In Proceedings of the 32nd International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 37), Francis Bach and David Blei (Eds.). PMLR, Lille, France, 1889--1897. https:\/\/proceedings.mlr.press\/v37\/schulman15.html"},{"key":"e_1_3_2_2_20_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. arXiv:1707.06347 [cs.LG]"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00599-w"},{"key":"e_1_3_2_2_22_1","volume-title":"Proceedings of the 14th ACM\/SIGEVO Conference on Foundations of Genetic Algorithms","author":"Strasser Shane","unstructured":"Shane Strasser and John W. Sheppard. 2017. Convergence of Factored Evolutionary Algorithms. In Proceedings of the 14th ACM\/SIGEVO Conference on Foundations of Genetic Algorithms (Copenhagen, Denmark) (FOGA '17). Association for Computing Machinery, New York, NY, USA, 81--94."},{"key":"e_1_3_2_2_23_1","volume-title":"Barto","author":"Sutton Richard S.","year":"2018","unstructured":"Richard S. Sutton and Andrew G. Barto. 2018. Reinforcement Learning: An Introduction (second ed.). The MIT Press."},{"key":"e_1_3_2_2_24_1","volume-title":"Learning from Delayed Rewards. Ph. D. Dissertation. Department of Computer Science","author":"Watkins Christopher","unstructured":"Christopher Watkins. 1989. Learning from Delayed Rewards. Ph. D. Dissertation. Department of Computer Science, Kings College, Cambridge University."},{"key":"e_1_3_2_2_25_1","unstructured":"Chao Yu Akash Velu Eugene Vinitsky Jiaxuan Gao Yu Wang Alexandre Bayen and Yi Wu. 2022. The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games. arXiv:2103.01955 [cs.LG]"}],"event":{"name":"GECCO '24: Genetic and Evolutionary Computation Conference","location":"Melbourne VIC Australia","acronym":"GECCO '24","sponsor":["SIGEVO ACM Special Interest Group on Genetic and Evolutionary Computation"]},"container-title":["Proceedings of the Genetic and Evolutionary Computation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3638529.3653992","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3638529.3653992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:56:49Z","timestamp":1750291009000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3638529.3653992"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,14]]},"references-count":25,"alternative-id":["10.1145\/3638529.3653992","10.1145\/3638529"],"URL":"https:\/\/doi.org\/10.1145\/3638529.3653992","relation":{},"subject":[],"published":{"date-parts":[[2024,7,14]]},"assertion":[{"value":"2024-07-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}