{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T02:49:11Z","timestamp":1774147751958,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003246","name":"NWO","doi-asserted-by":"publisher","award":["628.009.012"],"award-info":[{"award-number":["628.009.012"]}],"id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9533697","type":"proceedings-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T21:27:41Z","timestamp":1632173261000},"page":"1-8","source":"Crossref","is-referenced-by-count":5,"title":["Learning 2-opt Local Search from Heuristics as Expert Demonstrations"],"prefix":"10.1109","author":[{"given":"Paulo","family":"Da Costa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingqian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alp","family":"Akcay","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Uzay","family":"Kaymak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","author":"applegate","year":"2006","journal-title":"Concorde TSP Solver"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.dam.2005.05.020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1287\/opre.21.2.498"},{"key":"ref31","first-page":"1531","article-title":"A natural policy gradient","author":"kakade","year":"2002","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref37","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"Proceedings of the 5th International Conference on Learning Representations (ICLR)"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"williams","year":"1992","journal-title":"Machine Learning"},{"key":"ref35","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref34","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref10","author":"da costa","year":"2020","journal-title":"Learning 2-opt heuristics for the traveling salesman problem via deep reinforcement learning"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref11","first-page":"661","article-title":"Efficient reductions for imitation learning","author":"ross","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref12","article-title":"Fast policy learning through imitation and reinforcement","author":"cheng","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1057\/jors.1975.151"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s12532-009-0004-6"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-015-7744-1_2"},{"key":"ref16","first-page":"6281","article-title":"Learning to perform local rewriting for combinatorial optimization","author":"chen","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref18","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref28","author":"chen","year":"2020","journal-title":"Policy gradient from demonstration and curiosity"},{"key":"ref4","first-page":"2692","article-title":"Pointer networks","author":"vinyals","year":"2015","journal-title":"Proceedings of the 29th Conference on Neural Information Processing Systems (NIPS)"},{"key":"ref27","article-title":"Deep q-learning from demonstrations","author":"hester","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref3","article-title":"Machine learning for combinatorial optimization: a methodological tour d'horizon","author":"bengio","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref6","author":"joshi","year":"2019","journal-title":"An efficient graph convolutional network technique for the travelling salesman problem"},{"key":"ref29","first-page":"2469","article-title":"Policy optimization with demonstrations","volume":"80","author":"kang","year":"2018","journal-title":"Machine Learning Research"},{"key":"ref5","article-title":"Neural combinatorial optimization with reinforcement learning","author":"bello","year":"2017","journal-title":"Proceedings of the 5th International Conference on Learning Representations (ICLR)"},{"key":"ref8","article-title":"Attention, learn to solve routing problems!","author":"kool","year":"2019","journal-title":"Proceedings of the 7th International Conference on Learning Representations (ICLR)"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1007\/978-3-319-93031-2_12","article-title":"Learning heuristics for the tsp by policy gradient","author":"deudon","year":"2018","journal-title":"Proceedings of the 15th International Conference on the Integration of Constraint Programming Artificial Intelligence and Operations Research (CPAIOR)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-2217(99)00284-2"},{"key":"ref9","author":"wu","year":"2019","journal-title":"Learning improvement heuristics for solving the travelling salesman problem"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/0304-3975(77)90012-3"},{"key":"ref20","first-page":"2058","article-title":"Learning to search better than your teacher","author":"chang","year":"2015","journal-title":"Int Conference on Machine Learning"},{"key":"ref22","author":"alvarez","year":"2016","journal-title":"Online learning for strong branching approximation in branch-and-bound"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.29007\/7ksb"},{"key":"ref24","first-page":"15580","article-title":"Exact combinatorial optimization with graph convolutional neural networks","author":"gasse","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref41","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10080","article-title":"Learning to branch in mixed integer programming","author":"khalil","year":"2016","journal-title":"THIRTIETH AAAI Conference on Artificial Intelligence"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref25","author":"baltean-lugojan","year":"2019","journal-title":"Scoring positive semidefinite cutting planes for quadratic optimization via trained neural networks"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","location":"Shenzhen, China","start":{"date-parts":[[2021,7,18]]},"end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09533697.pdf?arnumber=9533697","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T19:40:46Z","timestamp":1673293246000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9533697\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9533697","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}