{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T10:51:55Z","timestamp":1781088715295,"version":"3.54.1"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030878962","type":"print"},{"value":"9783030878979","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-87897-9_21","type":"book-chapter","created":{"date-parts":[[2021,10,5]],"date-time":"2021-10-05T17:23:18Z","timestamp":1633454598000},"page":"229-239","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Applying and Comparing Policy Gradient Methods to Multi-echelon Supply Chains with Uncertain Demands and Lead Times"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4848-9453","authenticated-orcid":false,"given":"Julio C\u00e9sar","family":"Alves","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8600-5598","authenticated-orcid":false,"given":"Diego Mello da","family":"Silva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7238-0714","authenticated-orcid":false,"given":"Geraldo Robson","family":"Mateus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,10,6]]},"reference":[{"key":"21_CR1","unstructured":"Alves, J.C., Mateus, G.R.: Multi-echelon supply chains with uncertain seasonal demands and lead times using deep reinforcement learning. Submitted (2021)"},{"key":"21_CR2","unstructured":"Bergstra, J., Bardenet, R., Bengio, Y., K\u00e9gl, B.: Algorithms for hyper-parameter optimization. In: Proceedings of the 24th International Conference on Neural Information Processing Systems. NIPS 2011, Red Hook, NY, USA, pp. 2546\u20132554. Curran Associates Inc. (2011)"},{"key":"21_CR3","unstructured":"Colas, C., Sigaud, O., Oudeyer, P.Y.: A Hitchhiker\u2019s guide to statistical comparisons of reinforcement learning algorithms. In: ICLR Worskhop on Reproducibility, Nouvelle-Orl\u00e9ans, United States, May 2019. https:\/\/hal.archives-ouvertes.fr\/hal-02369859"},{"key":"21_CR4","unstructured":"Fujimoto, S., van Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, 10\u201315 Jul 2018, vol. 80, pp. 1587\u20131596. PMLR (2018). http:\/\/proceedings.mlr.press\/v80\/fujimoto18a.html"},{"key":"21_CR5","unstructured":"Geevers, K.: Deep reinforcement learning in inventory management. Master\u2019s thesis, University of Twente, December 2020. http:\/\/essay.utwente.nl\/85432\/"},{"key":"21_CR6","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3302881","author":"J Gijsbrechts","year":"2020","unstructured":"Gijsbrechts, J., Boute, R.N., Van Mieghem, J.A., Zhang, D.: Can deep reinforcement learning improve inventory management? performance on dual sourcing, lost sales and multi-echelon problems. SSRN (2020). https:\/\/doi.org\/10.2139\/ssrn.3302881","journal-title":"SSRN"},{"key":"21_CR7","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, 10\u201315 Jul 2018, vol. 80, pp. 1861\u20131870. PMLR (2018). http:\/\/proceedings.mlr.press\/v80\/haarnoja18b.html"},{"key":"21_CR8","doi-asserted-by":"publisher","unstructured":"Hacha\u00efchi, Y., Chemingui, Y., Affes, M.: A policy gradient based reinforcement learning method for supply chain management. In: 2020 4th International Conference on Advanced Systems and Emergent Technologies (IC$$\\_$$ASET), pp. 135\u2013140 (2020). https:\/\/doi.org\/10.1109\/IC_ASET49463.2020.9318258","DOI":"10.1109\/IC_ASET49463.2020.9318258"},{"key":"21_CR9","unstructured":"Hutse, V.: Reinforcement learning for inventory optimisation in multi-echelon supply chains. Master in business engineering, Gent University (2019). http:\/\/lib.ugent.be\/catalog\/rug01:002790831"},{"key":"21_CR10","unstructured":"Kemmer, L., von Kleist, H., de Rochebou\u00ebt, D., Tziortziotis, N., Read, J.: Reinforcement learning for supply chain optimization. In: European Workshop on Reinforcement Learning, vol. 14 (2018). https:\/\/ewrl.files.wordpress.com\/2018\/09\/ewrl_14_2018_paper_44.pdf"},{"key":"21_CR11","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"21_CR12","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: Balcan, M.F., Weinberger, K.Q. (eds.) Proceedings of The 33rd International Conference on Machine Learning. Proceedings of Machine Learning Research, 20\u201322 Jun 2016, New York, USA, vol. 48, pp. 1928\u20131937. PMLR (2016). http:\/\/proceedings.mlr.press\/v48\/mniha16.html"},{"issue":"7540","key":"21_CR13","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015). https:\/\/doi.org\/10.1038\/nature14236","journal-title":"Nature"},{"key":"21_CR14","unstructured":"Oroojlooyjadid, A.: Applications of machine learning in supply chains. Ph.D. thesis, Lehigh University (2019). https:\/\/preserve.lehigh.edu\/etd\/4364"},{"key":"21_CR15","doi-asserted-by":"publisher","unstructured":"Peng, Z., Zhang, Y., Feng, Y., Zhang, T., Wu, Z., Su, H.: Deep reinforcement learning approach for capacitated supply chain optimization under demand uncertainty. In: 2019 Chinese Automation Congress (CAC), pp. 3512\u20133517 (2019). https:\/\/doi.org\/10.1109\/CAC48633.2019.8997498","DOI":"10.1109\/CAC48633.2019.8997498"},{"key":"21_CR16","doi-asserted-by":"publisher","unstructured":"Perez, H.D., Hubbs, C.D., Li, C., Grossmann, I.E.: Algorithmic approaches to inventory management optimization. Processes 9(1) (2021). https:\/\/doi.org\/10.3390\/pr9010102","DOI":"10.3390\/pr9010102"},{"key":"21_CR17","unstructured":"Raffin, A., Hill, A., Ernestus, M., Gleave, A., Kanervisto, A., Dormann, N.: Stable baselines3 (2019). https:\/\/github.com\/DLR-RM\/stable-baselines3"},{"key":"21_CR18","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"issue":"7587","key":"21_CR19","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016). https:\/\/doi.org\/10.1038\/nature16961","journal-title":"Nature"},{"key":"21_CR20","unstructured":"Sutton, R., Barto, A.: Reinforcement learning, second edition: an introduction. In: Adaptive Computation and Machine Learning series. MIT Press (2018). https:\/\/mitpress.mit.edu\/books\/reinforcement-learning-second-edition"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence and Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87897-9_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,5]],"date-time":"2021-10-05T17:31:13Z","timestamp":1633455073000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87897-9_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030878962","9783030878979"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87897-9_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"6 October 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICAISC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Intelligence and Soft Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icaisc2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/icaisc2021.icaisc.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Own Online System","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"195","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"89","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"46% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}