Jonas Stein, Florentin D Hildebrandt, Barrett W Thomas, Marlin W Ulmer
{"title":"为带返工的动态技术人员路由学习与状态相关的策略参数化","authors":"Jonas Stein, Florentin D Hildebrandt, Barrett W Thomas, Marlin W Ulmer","doi":"arxiv-2409.01815","DOIUrl":null,"url":null,"abstract":"Home repair and installation services require technicians to visit customers\nand resolve tasks of different complexity. Technicians often have heterogeneous\nskills and working experiences. The geographical spread of customers makes\nachieving only perfect matches between technician skills and task requirements\nimpractical. Additionally, technicians are regularly absent due to sickness.\nWith non-perfect assignments regarding task requirement and technician skill,\nsome tasks may remain unresolved and require a revisit and rework. Companies\nseek to minimize customer inconvenience due to delay. We model the problem as a\nsequential decision process where, over a number of service days, customers\nrequest service while heterogeneously skilled technicians are routed to serve\ncustomers in the system. Each day, our policy iteratively builds tours by\nadding \"important\" customers. The importance bases on analytical considerations\nand is measured by respecting routing efficiency, urgency of service, and risk\nof rework in an integrated fashion. We propose a state-dependent balance of\nthese factors via reinforcement learning. A comprehensive study shows that\ntaking a few non-perfect assignments can be quite beneficial for the overall\nservice quality. We further demonstrate the value provided by a state-dependent\nparametrization.","PeriodicalId":501479,"journal":{"name":"arXiv - CS - Artificial Intelligence","volume":"248 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Learning State-Dependent Policy Parametrizations for Dynamic Technician Routing with Rework\",\"authors\":\"Jonas Stein, Florentin D Hildebrandt, Barrett W Thomas, Marlin W Ulmer\",\"doi\":\"arxiv-2409.01815\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Home repair and installation services require technicians to visit customers\\nand resolve tasks of different complexity. Technicians often have heterogeneous\\nskills and working experiences. The geographical spread of customers makes\\nachieving only perfect matches between technician skills and task requirements\\nimpractical. Additionally, technicians are regularly absent due to sickness.\\nWith non-perfect assignments regarding task requirement and technician skill,\\nsome tasks may remain unresolved and require a revisit and rework. Companies\\nseek to minimize customer inconvenience due to delay. We model the problem as a\\nsequential decision process where, over a number of service days, customers\\nrequest service while heterogeneously skilled technicians are routed to serve\\ncustomers in the system. Each day, our policy iteratively builds tours by\\nadding \\\"important\\\" customers. The importance bases on analytical considerations\\nand is measured by respecting routing efficiency, urgency of service, and risk\\nof rework in an integrated fashion. We propose a state-dependent balance of\\nthese factors via reinforcement learning. A comprehensive study shows that\\ntaking a few non-perfect assignments can be quite beneficial for the overall\\nservice quality. We further demonstrate the value provided by a state-dependent\\nparametrization.\",\"PeriodicalId\":501479,\"journal\":{\"name\":\"arXiv - CS - Artificial Intelligence\",\"volume\":\"248 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Artificial Intelligence\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.01815\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Artificial Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.01815","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Learning State-Dependent Policy Parametrizations for Dynamic Technician Routing with Rework
Home repair and installation services require technicians to visit customers
and resolve tasks of different complexity. Technicians often have heterogeneous
skills and working experiences. The geographical spread of customers makes
achieving only perfect matches between technician skills and task requirements
impractical. Additionally, technicians are regularly absent due to sickness.
With non-perfect assignments regarding task requirement and technician skill,
some tasks may remain unresolved and require a revisit and rework. Companies
seek to minimize customer inconvenience due to delay. We model the problem as a
sequential decision process where, over a number of service days, customers
request service while heterogeneously skilled technicians are routed to serve
customers in the system. Each day, our policy iteratively builds tours by
adding "important" customers. The importance bases on analytical considerations
and is measured by respecting routing efficiency, urgency of service, and risk
of rework in an integrated fashion. We propose a state-dependent balance of
these factors via reinforcement learning. A comprehensive study shows that
taking a few non-perfect assignments can be quite beneficial for the overall
service quality. We further demonstrate the value provided by a state-dependent
parametrization.