0 of 0       
Essec\Faculty\Model\Contribution {#2233 ▼
  #_index: "academ_contributions"
  #_id: "15264"
  #_source: array:26 [
    "id" => "15264"
    "slug" => "15264-reinforcement-learning-approaches-for-the-orienteering-problem-with-stochastic-and-dynamic-release-dates 15264-reinforcement-learning-approaches-for-the-orienteering-problem-with-stochastic-and-dynamic-rel "
    "yearMonth" => "2024-09"
    "year" => "2024"
    "title" => "Reinforcement Learning Approaches for the Orienteering Problem with Stochastic and Dynamic Release Dates Reinforcement Learning Approaches for the Orienteering Problem with Stochastic and Dynamic Release D "
    "description" => "LI, Y., ARCHETTI, C. et LJUBIC, I. (2024). Reinforcement Learning Approaches for the Orienteering Problem with Stochastic and Dynamic Release Dates. <i>Transportation Science</i>, 58(5), pp. 1143-1165. LI, Y., ARCHETTI, C. et LJUBIC, I. (2024). Reinforcement Learning Approaches for the Orienteering Pr "
    "authors" => array:3 [
      0 => array:3 [
        "name" => "LJUBIC Ivana"
        "bid" => "B00683004"
        "slug" => "ljubic-ivana"
      ]
      1 => array:1 [
        "name" => "LI Yuanyuan"
      ]
      2 => array:1 [
        "name" => "ARCHETTI Claudia"
      ]
    ]
    "ouvrage" => ""
    "keywords" => array:5 [
      0 => "reinforcement learning"
      1 => "two-stage stochastic ILP model"
      2 => "branch-and-cut"
      3 => "Markov decision process"
      4 => "orienteering problem"
    ]
    "updatedAt" => "2024-10-07 13:32:16"
    "publicationUrl" => "https://doi.org/10.1287/trsc.2022.0366"
    "publicationInfo" => array:3 [
      "pages" => "1143-1165"
      "volume" => "58"
      "number" => "5"
    ]
    "type" => array:2 [
      "fr" => "Articles"
      "en" => "Journal articles"
    ]
    "support_type" => array:2 [
      "fr" => "Revue scientifique"
      "en" => "Scientific journal"
    ]
    "countries" => array:2 [
      "fr" => null
      "en" => null
    ]
    "abstract" => array:2 [
      "fr" => "In this paper, we study a sequential decision-making problem faced by e-commerce carriers related to when to send out a vehicle from the central depot to serve customer requests and in which order to provide the service, under the assumption that the time at which parcels arrive at the depot is stochastic and dynamic. The objective is to maximize the expected number of parcels that can be delivered during service hours. We propose two reinforcement learning (RL) approaches for solving this problem. These approaches rely on a look-ahead strategy in which future release dates are sampled in a Monte Carlo fashion, and a batch approach is used to approximate future routes. Both RL approaches are based on value function approximation: One combines it with a consensus function (VFA-CF) and the other one with a two-stage stochastic integer linear programming model (VFA-2S). VFA-CF and VFA-2S do not need extensive training as they are based on very few hyperparameters and make good use of integer linear programming (ILP) and branch-and-cut–based exact methods to improve the quality of decisions. We also establish sufficient conditions for partial characterization of optimal policy and integrate them into VFA-CF/VFA-2S. In an empirical study, we conduct a competitive analysis using upper bounds with perfect information. We also show that VFA-CF and VFA-2S greatly outperform alternative approaches that (1) do not rely on future information (2) are based on point estimation of future information, (3) use heuristics rather than exact methods, or (4) use exact evaluations of future rewards. In this paper, we study a sequential decision-making problem faced by e-commerce carriers related to "
      "en" => "In this paper, we study a sequential decision-making problem faced by e-commerce carriers related to when to send out a vehicle from the central depot to serve customer requests and in which order to provide the service, under the assumption that the time at which parcels arrive at the depot is stochastic and dynamic. The objective is to maximize the expected number of parcels that can be delivered during service hours. We propose two reinforcement learning (RL) approaches for solving this problem. These approaches rely on a look-ahead strategy in which future release dates are sampled in a Monte Carlo fashion, and a batch approach is used to approximate future routes. Both RL approaches are based on value function approximation: One combines it with a consensus function (VFA-CF) and the other one with a two-stage stochastic integer linear programming model (VFA-2S). VFA-CF and VFA-2S do not need extensive training as they are based on very few hyperparameters and make good use of integer linear programming (ILP) and branch-and-cut–based exact methods to improve the quality of decisions. We also establish sufficient conditions for partial characterization of optimal policy and integrate them into VFA-CF/VFA-2S. In an empirical study, we conduct a competitive analysis using upper bounds with perfect information. We also show that VFA-CF and VFA-2S greatly outperform alternative approaches that (1) do not rely on future information (2) are based on point estimation of future information, (3) use heuristics rather than exact methods, or (4) use exact evaluations of future rewards. In this paper, we study a sequential decision-making problem faced by e-commerce carriers related to "
    ]
    "authors_fields" => array:2 [
      "fr" => "Systèmes d’Information, Sciences de la Décision et Statistiques"
      "en" => "Information Systems, Decision Sciences and Statistics"
    ]
    "indexedAt" => "2025-04-02T10:21:47.000Z"
    "docTitle" => "Reinforcement Learning Approaches for the Orienteering Problem with Stochastic and Dynamic Release Dates Reinforcement Learning Approaches for the Orienteering Problem with Stochastic and Dynamic Release D "
    "docSurtitle" => "Articles"
    "authorNames" => "<a href="/cv/ljubic-ivana">LJUBIC Ivana</a>, LI Yuanyuan, ARCHETTI Claudia"
    "docDescription" => "<span class="document-property-authors">LJUBIC Ivana, LI Yuanyuan, ARCHETTI Claudia</span><br><span class="document-property-authors_fields">Systèmes d’Information, Sciences de la Décision et Statistiques</span> | <span class="document-property-year">2024</span> <span class="document-property-authors">LJUBIC Ivana, LI Yuanyuan, ARCHETTI Claudia</span><br><span  "
    "keywordList" => "<a href="#">reinforcement learning</a>, <a href="#">two-stage stochastic ILP model</a>, <a href="#">branch-and-cut</a>, <a href="#">Markov decision process</a>, <a href="#">orienteering problem</a> <a href="#">reinforcement learning</a>, <a href="#">two-stage stochastic ILP model</a>, <a href="#"> "
    "docPreview" => "<b>Reinforcement Learning Approaches for the Orienteering Problem with Stochastic and Dynamic Release Dates</b><br><span>2024-09 | Articles </span> <b>Reinforcement Learning Approaches for the Orienteering Problem with Stochastic and Dynamic Releas "
    "docType" => "research"
    "publicationLink" => "<a href="https://doi.org/10.1287/trsc.2022.0366" target="_blank">Reinforcement Learning Approaches for the Orienteering Problem with Stochastic and Dynamic Release Dates</a> <a href="https://doi.org/10.1287/trsc.2022.0366" target="_blank">Reinforcement Learning Approaches f "
  ]
  +lang: "fr"
  +"_type": "_doc"
  +"_score": 8.458376
  +"parent": null
}