{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:17:43Z","timestamp":1750220263581,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,4,28]],"date-time":"2022-04-28T00:00:00Z","timestamp":1651104000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,4,28]]},"DOI":"10.1145\/3535782.3535803","type":"proceedings-article","created":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T21:27:57Z","timestamp":1658179677000},"page":"152-161","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Research on Order Acceptance Strategy for Military manufactures Based on Semi-Markov Average Reward Reinforcement Learning"],"prefix":"10.1145","author":[{"given":"Xiaodi","family":"Yi","sequence":"first","affiliation":[{"name":"National University of Defense Technology, China"}]},{"given":"Kuihua","family":"Huang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, China"}]},{"given":"Jincai","family":"Huang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, China"}]},{"given":"Jing","family":"Qian","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, China"}]},{"given":"Jie","family":"Kang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, China"}]}],"member":"320","published-online":{"date-parts":[[2022,7,18]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2005.11.012"},{"key":"e_1_3_2_1_2_1","volume-title":"Recent developments in deterministic sequencing and scheduling: a survey [M]","author":"LAWLER E, LENSTRA J, RINNOOY K","year":"1982","unstructured":"LAWLER E, LENSTRA J, RINNOOY K A. Recent developments in deterministic sequencing and scheduling: a survey [M]. DEMPSTER M, LENSTRA J, RINNOOY K A, editors. Deterministic and stochastic scheduling, 1982: 35 - 73."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.16.3.234"},{"key":"e_1_3_2_1_4_1","first-page":"82","article-title":"An advanced order acceptance model for hybrid production strategy[J].","volume":"2020","author":"Abedi Arash","unstructured":"Arash Abedi,Weihang Zhu. An advanced order acceptance model for hybrid production strategy[J].Journal of Manufacturing System,2020,55:82-93.","journal-title":"Journal of Manufacturing System"},{"key":"e_1_3_2_1_5_1","first-page":"145","article-title":"production planning with order acceptance and demand uncertainty[J].","volume":"2018","author":"Aouam Tarik","unstructured":"Tarik Aouam,Kobe Geryl,Kunal Kumar,Nadjib Brahimi. production planning with order acceptance and demand uncertainty[J].Computers & Operations Research,2018,91:145-159.","journal-title":"Computers & Operations Research"},{"issue":"02","key":"e_1_3_2_1_6_1","first-page":"34","article-title":"Order acceptance strategy based on limited production capacity and output caching[J]","volume":"2008","author":"Zhang","unstructured":"Zhang X,Ma S-H. Order acceptance strategy based on limited production capacity and output caching[J]. Industrial Engineering and Management,2008(02):34-38+43+79.","journal-title":"Industrial Engineering and Management"},{"key":"e_1_3_2_1_7_1","first-page":"87","article-title":"Order pricing and acceptance strategies for MTO companies based on revenue management[J]","volume":"2011","unstructured":"Fan, L.F.,Chen, X. Order pricing and acceptance strategies for MTO companies based on revenue management[J]. Systems Engineering,2011,29(02):87-93.","journal-title":"Systems Engineering"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Li Xin Ventura Jose A.. Exact algorithms for a joint order acceptance and scheduling problem[J]. International Journal of Production Economics 2019(prepublish).","DOI":"10.1016\/j.ijpe.2019.107516"},{"key":"e_1_3_2_1_9_1","first-page":"108","article-title":"Integrated decision making of order selection and scheduling for MTO enterprises considering demand time series correlation[J]","volume":"2017","unstructured":"Gao, Huahua, Dan, Bin, Yan, Jian. Integrated decision making of order selection and scheduling for MTO enterprises considering demand time series correlation[J]. Journal of Management Engineering,2017,31(03):108-116.","journal-title":"Journal of Management Engineering"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Walter O. Rom Susan A. Slotnick. Order acceptance using genetic algorithms[J]. Computers and Operations Research 2008 36(6).","DOI":"10.1016\/j.cor.2008.04.010"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Fabrice Talla Nobibon Roel Leus. Exact algorithms for a generalization of the order acceptance and scheduling problem in a single-machine environment [J]. Computers and Operations Research 2010 38(1).","DOI":"10.1016\/j.cor.2010.06.003"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Bahriye Cesaret Ceyda O\u011fuz F. Sibel Salman. A tabu search algorithm for order acceptance and scheduling[J]. Computers and Operations Research 2010 39(6).","DOI":"10.1016\/j.cor.2010.09.018"},{"key":"e_1_3_2_1_13_1","article-title":"Reinforcement learning for joint pricing, lead-time and scheduling decisions in make-to-order systems[J]","volume":"2012","author":"Li Xueping","unstructured":"Xueping Li,Jiao Wang,Rapinder Sawhney. Reinforcement learning for joint pricing, lead-time and scheduling decisions in make-to-order systems[J]. European Journal of Operational Research,2012,221(1).","journal-title":"European Journal of Operational Research"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Facundo Arredondo Ernesto Martinez. Learning and adaptation of a policy for dynamic order acceptance in make-to-order manufacturing[J]. Computers & Industrial Engineering 2009 58(1).","DOI":"10.1016\/j.cie.2009.08.005"},{"key":"e_1_3_2_1_15_1","first-page":"976","article-title":"Order acceptance strategy of order production method companies based on average reinforcement learning[J]","volume":"2013","unstructured":"Hao, Zuan, Yu, Jianjun, Zhou, Wenhui. Order acceptance strategy of order production method companies based on average reinforcement learning[J]. Computer Applications,2013,33(04):976-979.","journal-title":"Computer Applications"},{"key":"e_1_3_2_1_16_1","unstructured":"Wang Lei Xu Shaoyun Zhao Yang Zhao Qiuhong. A multi-node order acceptance model with finite buffer and algorithm[J] China Management Science 2015 23(12):135-141."},{"key":"e_1_3_2_1_17_1","first-page":"697","article-title":"selection and scheduling with leadtime flexibilith[J]","volume":"2004","author":"Charnsirisakskul","unstructured":"Charnsirisakskul K,Griffin P M,Keskinocak P.Order selection and scheduling with leadtime flexibilith[J]. IIE Transactions,2004,36(7):697-707.","journal-title":"IIE Transactions"},{"key":"e_1_3_2_1_18_1","first-page":"3121","article-title":"Order acceptance strategy for order production-based firms based on reinforcement learning[J]","volume":"2014","author":"Xiaohuan Wang","unstructured":"Wang Xiaohuan,Wang Ningning,Fan Zhiping. Order acceptance strategy for order production-based firms based on reinforcement learning[J]. Systems Engineering Theory and Practice,2014,34(12):3121-3129.","journal-title":"Systems Engineering Theory and Practice"},{"key":"e_1_3_2_1_19_1","first-page":"112742","article-title":"real-time order acceptance and scheduling problems in a flow shop Environment using hybrid GA-PSO algorithm[J].","volume":"2019","author":"Rahman H. F.","unstructured":"H. F. Rahman, M. N. Janardhanan and I. E. Nielsen. real-time order acceptance and scheduling problems in a flow shop Environment using hybrid GA-PSO algorithm[J].IEEE Access,2019,7:112742-112755.","journal-title":"IEEE Access"},{"issue":"08","key":"e_1_3_2_1_20_1","first-page":"1372","article-title":"Research on average reward reinforcement learning algorithm[J]","volume":"2007","author":"Yang Gao","unstructured":"Gao Yang,Zhou Ruyi,Wang Hao,Cao Zhixin. Research on average reward reinforcement learning algorithm[J]. Journal of Computer Science,2007(08):1372-1378.","journal-title":"Journal of Computer Science"},{"key":"e_1_3_2_1_21_1","first-page":"874","article-title":"Dynamic order acceptance and capacity planning on a single bottleneck resource [J].","volume":"2007","author":"HERBOTS J, HERROELEN W, LEUS","unstructured":"HERBOTS J, HERROELEN W, LEUS R. Dynamic order acceptance and capacity planning on a single bottleneck resource [J].Naval Research Logistics,2007,54(8): 874-889.","journal-title":"Naval Research Logistics"},{"key":"e_1_3_2_1_22_1","first-page":"167","article-title":"Reinforcement learning versus heuris-tics for order acceptance on a single resource[J].","volume":"2007","author":"HING M","unstructured":"HING M, van HARTEN M. Reinforcement learning versus heuris-tics for order acceptance on a single resource[J].Journal of Heuristics,2007, 13( 2) : 167- 187.","journal-title":"Journal of Heuristics"},{"key":"e_1_3_2_1_23_1","first-page":"697","article-title":"Order selection and scheduling with leadtime flexibility[J].","volume":"2004","author":"Charnsirisakskul","unstructured":"Charnsirisakskul K,Griffin P M,Keskinocak P. Order selection and scheduling with leadtime flexibility[J].IIE Transactions,2004,36(7):697-707.","journal-title":"IIE Transactions"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/NNSP.1992.253713"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Kaelbling L P Littman M L Moore A P. Reinforcement learning: a survey Journal of Artificial Intelligence Research 1996 4:237-285.","DOI":"10.1613\/jair.301"},{"key":"e_1_3_2_1_26_1","volume-title":"Reinforcement learning :An Introduction","author":"Sutton R S","year":"1998","unstructured":"Sutton R S, Barto A G. Reinforcement learning :An Introduction.Cambridge MA:MIT Press,1998."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"e_1_3_2_1_28_1","first-page":"455","article-title":"Solving Semi-Markov Decision Problems using Average Reward Reinforcement Learning [J]","volume":"45","author":"Tapas","year":"1999","unstructured":"Tapas K, Das, Abhijit Gosavi. Solving Semi-Markov Decision Problems using Average Reward Reinforcement Learning [J]. Management Science, 1999, 45:455-620","journal-title":"Management Science"}],"event":{"name":"MSIE 2022: 2022 4th International Conference on Management Science and Industrial Engineering","acronym":"MSIE 2022","location":"Chiang Mai Thailand"},"container-title":["Proceedings of the 4th International Conference on Management Science and Industrial Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3535782.3535803","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3535782.3535803","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:55Z","timestamp":1750188655000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3535782.3535803"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,28]]},"references-count":28,"alternative-id":["10.1145\/3535782.3535803","10.1145\/3535782"],"URL":"https:\/\/doi.org\/10.1145\/3535782.3535803","relation":{},"subject":[],"published":{"date-parts":[[2022,4,28]]},"assertion":[{"value":"2022-07-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}