{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,15]],"date-time":"2026-11-15T20:44:36Z","timestamp":1794775476982,"version":"4.9.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T00:00:00Z","timestamp":1722902400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T00:00:00Z","timestamp":1722902400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Auton Agent Multi-Agent Syst"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s10458-024-09669-2","type":"journal-article","created":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T04:14:30Z","timestamp":1722917670000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Carbon trading supply chain management based on constrained deep reinforcement learning"],"prefix":"10.1007","volume":"38","author":[{"given":"Qinghao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaodong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,8,6]]},"reference":[{"issue":"7153","key":"9669_CR1","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1038\/448550a","volume":"448","author":"W Thuiller","year":"2007","unstructured":"Thuiller, W. (2007). Climate change and the ecologist. Nature, 448(7153), 550\u2013552.","journal-title":"Nature"},{"issue":"4","key":"9669_CR2","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1257\/jep.7.4.27","volume":"7","author":"JP Weyant","year":"1993","unstructured":"Weyant, J. P. (1993). Costs of reducing global carbon emissions. Journal of Economic Perspectives, 7(4), 27\u201346.","journal-title":"Journal of Economic Perspectives"},{"key":"9669_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jclepro.2015.04.098","volume":"103","author":"D Huisingh","year":"2015","unstructured":"Huisingh, D., Zhang, Z., Moore, J. C., Qiao, Q., & Li, Q. (2015). Recent advances in carbon emissions reduction: Policies, technologies, monitoring, assessment and modeling. Journal of Cleaner Production, 103, 1\u201312.","journal-title":"Journal of Cleaner Production"},{"issue":"2","key":"9669_CR4","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1080\/13563460903556049","volume":"15","author":"CL Spash","year":"2010","unstructured":"Spash, C. L. (2010). The brave new world of carbon trading. New Political Economy, 15(2), 169\u2013195.","journal-title":"New Political Economy"},{"issue":"10","key":"9669_CR5","doi-asserted-by":"publisher","first-page":"6040","DOI":"10.1016\/j.enpol.2011.07.003","volume":"39","author":"S Perdan","year":"2011","unstructured":"Perdan, S., & Azapagic, A. (2011). Carbon trading: Current schemes and future developments. Energy Policy, 39(10), 6040\u20136054.","journal-title":"Energy Policy"},{"issue":"1","key":"9669_CR6","first-page":"S45","volume":"7","author":"R Lamming","year":"1996","unstructured":"Lamming, R., & Hampson, J. (1996). The environment as a supply chain management issue. British Journal of Management, 7(1), S45\u2013S62.","journal-title":"British Journal of Management"},{"key":"9669_CR7","doi-asserted-by":"crossref","unstructured":"Stadtler, H. (2014). Supply chain management and advanced planning: Concepts, models, software, and case studies, 3\u201328","DOI":"10.1007\/978-3-642-55309-7_1"},{"issue":"1","key":"9669_CR8","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1016\/0377-2217(89)90463-3","volume":"38","author":"SK Goyal","year":"1989","unstructured":"Goyal, S. K., & Satir, A. T. (1989). Joint replenishment inventory control: Deterministic and stochastic models. European Journal of Operational Research, 38(1), 2\u201313.","journal-title":"European Journal of Operational Research"},{"key":"9669_CR9","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1287\/msom.3.3.211.9893","volume":"3","author":"G Cachon","year":"2001","unstructured":"Cachon, G. (2001). Managing a retailer\u2019s shelf space, inventory, and transportation. Manufacturing & Service Operations Management, 3, 211\u2013229.","journal-title":"Manufacturing & Service Operations Management"},{"key":"9669_CR10","doi-asserted-by":"publisher","first-page":"108120","DOI":"10.1016\/j.ijpe.2021.108120","volume":"236","author":"Y Yang","year":"2021","unstructured":"Yang, Y., Lin, J., Liu, G., & Zhou, L. (2021). The behavioural causes of bullwhip effect in supply chains: A systematic literature review. International Journal of Production Economics, 236, 108120.","journal-title":"International Journal of Production Economics"},{"key":"9669_CR11","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223","volume-title":"Constrained Markov decision processes","author":"E Altman","year":"2021","unstructured":"Altman, E. (2021). Constrained Markov decision processes. Routledge."},{"issue":"1","key":"9669_CR12","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1287\/msom.2020.0939","volume":"24","author":"A Oroojlooyjadid","year":"2022","unstructured":"Oroojlooyjadid, A., Nazari, M., Snyder, L. V., & Tak\u00e1\u010d, M. (2022). A deep q-network for the beer game: Deep reinforcement learning for inventory optimization. Manufacturing & Service Operations Management, 24(1), 285\u2013304.","journal-title":"Manufacturing & Service Operations Management"},{"issue":"3","key":"9669_CR13","doi-asserted-by":"publisher","first-page":"1349","DOI":"10.1287\/msom.2021.1064","volume":"24","author":"J Gijsbrechts","year":"2022","unstructured":"Gijsbrechts, J., Boute, R. N., Van Mieghem, J. A., & Zhang, D. J. (2022). Can deep reinforcement learning improve inventory management? Performance on lost sales, dual-sourcing, and multi-echelon problems. Manufacturing & Service Operations Management, 24(3), 1349\u20131368.","journal-title":"Manufacturing & Service Operations Management"},{"issue":"2","key":"9669_CR14","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1016\/j.ejor.2021.07.016","volume":"298","author":"RN Boute","year":"2022","unstructured":"Boute, R. N., Gijsbrechts, J., Van Jaarsveld, W., & Vanvuchelen, N. (2022). Deep reinforcement learning for inventory control: A roadmap. European Journal of Operational Research, 298(2), 401\u2013412.","journal-title":"European Journal of Operational Research"},{"key":"9669_CR15","doi-asserted-by":"crossref","unstructured":"Liu, X., Alexopoulos, C., Hu, H., Han, S., Peng, Y., Qi, Y. (2023). Deep reinforcement learning for large-scale inventory management. Available at SSRN 4490327","DOI":"10.2139\/ssrn.4490327"},{"issue":"6","key":"9669_CR16","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1007\/s11518-022-5544-6","volume":"31","author":"Q Wang","year":"2022","unstructured":"Wang, Q., Peng, Y., & Yang, Y. (2022). Solving inventory management problems through deep reinforcement learning. Journal of Systems Science and Systems Engineering, 31(6), 677\u2013689.","journal-title":"Journal of Systems Science and Systems Engineering"},{"key":"9669_CR17","doi-asserted-by":"publisher","first-page":"1308","DOI":"10.1287\/ijoc.2022.0136","volume":"35","author":"L B\u00f6ttcher","year":"2023","unstructured":"B\u00f6ttcher, L., Asikis, T., & Fragkos, I. (2023). Control of dual-sourcing inventory systems using recurrent neural networks. INFORMS Journal on Computing, 35, 1308\u20131328.","journal-title":"INFORMS Journal on Computing"},{"key":"9669_CR18","doi-asserted-by":"crossref","unstructured":"Liu, X., Hu, M., Peng, Y., Yang, Y. (2022). Multi-agent deep reinforcement learning for multi-echelon inventory management. Available at SSRN","DOI":"10.2139\/ssrn.4262186"},{"issue":"2","key":"9669_CR19","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1108\/JMTM-09-2017-0188","volume":"29","author":"C Das","year":"2018","unstructured":"Das, C., & Jharkharia, S. (2018). Low carbon supply chain: A state-of-the-art literature review. Journal of Manufacturing Technology Management, 29(2), 398\u2013428.","journal-title":"Journal of Manufacturing Technology Management"},{"issue":"1","key":"9669_CR20","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1109\/TASE.2012.2203304","volume":"10","author":"S Benjaafar","year":"2013","unstructured":"Benjaafar, S., Li, Y., & Daskin, M. (2013). Carbon footprint and the management of supply chains: Insights from simple models. IEEE Transactions on Automation Science and Engineering, 10(1), 99\u2013116.","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"issue":"1","key":"9669_CR21","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.ijpe.2010.01.018","volume":"128","author":"B Sundarakani","year":"2010","unstructured":"Sundarakani, B., de Souza, R., Goh, M., Wagner, S. M., & Manikandan, S. (2010). Modeling carbon footprints across the supply chain. International Journal of Production Economics, 128(1), 43\u201350. Integrating the Global Supply Chain.","journal-title":"International Journal of Production Economics"},{"key":"9669_CR22","doi-asserted-by":"publisher","first-page":"123220","DOI":"10.1016\/j.jclepro.2020.123220","volume":"276","author":"X Xia","year":"2020","unstructured":"Xia, X., Li, C., & Zhu, Q. (2020). Game analysis for the impact of carbon trading on low-carbon supply chain. Journal of Cleaner Production, 276, 123220.","journal-title":"Journal of Cleaner Production"},{"issue":"21","key":"9669_CR23","doi-asserted-by":"publisher","first-page":"6588","DOI":"10.1080\/00207543.2015.1005761","volume":"53","author":"M Brandenburg","year":"2015","unstructured":"Brandenburg, M. (2015). Low carbon supply chain configuration for a new product-a goal programming approach. International Journal of Production Research, 53(21), 6588\u20136610.","journal-title":"International Journal of Production Research"},{"key":"9669_CR24","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1016\/j.jclepro.2018.09.038","volume":"205","author":"H Peng","year":"2018","unstructured":"Peng, H., Pang, T., & Cong, J. (2018). Coordination contracts for a supply chain with yield uncertainty and low-carbon preference. Journal of Cleaner Production, 205, 291\u2013302.","journal-title":"Journal of Cleaner Production"},{"issue":"3","key":"9669_CR25","doi-asserted-by":"publisher","first-page":"542","DOI":"10.2507\/IJSIMM15(3)CO12","volume":"15","author":"G Hua","year":"2016","unstructured":"Hua, G., Cheng, T., Zhang, Y., Zhang, J., & Wang, S. (2016). Carbon-constrained perishable inventory management with freshness-dependent demand. International Journal of Simulation Modelling, 15(3), 542\u2013552.","journal-title":"International Journal of Simulation Modelling"},{"key":"9669_CR26","doi-asserted-by":"publisher","first-page":"106207","DOI":"10.1016\/j.cie.2019.106207","volume":"139","author":"Y-S Huang","year":"2020","unstructured":"Huang, Y.-S., Fang, C.-C., & Lin, Y.-A. (2020). Inventory management in supply chains with consideration of logistics, green investment and different carbon emissions policies. Computers & Industrial Engineering, 139, 106207.","journal-title":"Computers & Industrial Engineering"},{"issue":"7553","key":"9669_CR27","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436\u2013444.","journal-title":"Nature"},{"issue":"1","key":"9669_CR28","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1038\/nmeth.3707","volume":"13","author":"N Rusk","year":"2016","unstructured":"Rusk, N. (2016). Deep learning. Nature Methods, 13(1), 35\u201335.","journal-title":"Nature Methods"},{"key":"9669_CR29","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling, L. P., Littman, M. L., & Moore, A. W. (1996). Reinforcement learning: A survey. Journal of Artificial Intelligence Research, 4, 237\u2013285.","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"3","key":"9669_CR30","first-page":"729","volume":"12","author":"MA Wiering","year":"2012","unstructured":"Wiering, M. A., & Van Otterlo, M. (2012). Reinforcement learning. Adaptation, Learning, and Optimization, 12(3), 729.","journal-title":"Adaptation, Learning, and Optimization"},{"key":"9669_CR31","volume-title":"Reinforcement learning: An introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction. MIT Press."},{"issue":"7587","key":"9669_CR32","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., Van Den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016). Mastering the game of go with deep neural networks and tree search. Nature, 529(7587), 484\u2013489.","journal-title":"Nature"},{"issue":"6419","key":"9669_CR33","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1126\/science.aar6404","volume":"362","author":"D Silver","year":"2018","unstructured":"Silver, D., Hubert, T., Schrittwieser, J., Antonoglou, I., Lai, M., Guez, A., Lanctot, M., Sifre, L., Kumaran, D., Graepel, T., et al. (2018). A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science, 362(6419), 1140\u20131144.","journal-title":"Science"},{"issue":"7782","key":"9669_CR34","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., Babuschkin, I., Czarnecki, W. M., Mathieu, M., Dudzik, A., Chung, J., Choi, D. H., Powell, R., Ewalds, T., Georgiev, P., et al. (2019). Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature, 575(7782), 350\u2013354.","journal-title":"Nature"},{"issue":"7540","key":"9669_CR35","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529\u2013533.","journal-title":"Nature"},{"key":"9669_CR36","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O. (2017). Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347"},{"key":"9669_CR37","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S. (2018). Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International conference on machine learning, pp. 1861\u20131870. PMLR"},{"key":"9669_CR38","unstructured":"Achiam, J., Held, D., Tamar, A., Abbeel, P. (2017). Constrained policy optimization. In: International conference on machine learning, pp. 22\u201331. PMLR"},{"key":"9669_CR39","unstructured":"Ray, A., Achiam, J., & Amodei, D. (2019). Benchmarking safe exploration in deep reinforcement learning. 7(1), 2. arXiv:1910.01708."},{"key":"9669_CR40","first-page":"15338","volume":"33","author":"Y Zhang","year":"2020","unstructured":"Zhang, Y., Vuong, Q., & Ross, K. (2020). First order constrained optimization in policy space. Advances in Neural Information Processing Systems, 33, 15338\u201315349.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"9669_CR41","unstructured":"Yang, F. (2023). Exploring safe reinforcement learning for sequential decision making. PhD thesis, Carnegie Mellon University Pittsburgh"},{"issue":"1","key":"9669_CR42","first-page":"1437","volume":"16","author":"J Garc\u0131a","year":"2015","unstructured":"Garc\u0131a, J., & Fern\u00e1ndez, F. (2015). A comprehensive survey on safe reinforcement learning. Journal of Machine Learning Research, 16(1), 1437\u20131480.","journal-title":"Journal of Machine Learning Research"},{"key":"9669_CR43","doi-asserted-by":"crossref","unstructured":"Isele, D., Nakhaei, A., Fujimura, K. (2018). Safe reinforcement learning on autonomous vehicles. In: 2018 IEEE\/RSJ international conference on intelligent robots and systems (IROS), pp. 1\u2013 6. IEEE","DOI":"10.1109\/IROS.2018.8593420"},{"key":"9669_CR44","doi-asserted-by":"crossref","unstructured":"Mirchevska, B., Pek, C., Werling, M., Althoff, M., Boedecker, J. (2018). High-level decision making for safe and reasonable autonomous lane changing using reinforcement learning. In: 2018 21st international conference on intelligent transportation systems (ITSC), pp. 2156\u20132162. IEEE","DOI":"10.1109\/ITSC.2018.8569448"},{"key":"9669_CR45","unstructured":"Gu, S., Yang, L., Du, Y., Chen, G., Walter, F., Wang, J., Yang, Y., Knoll, A. (2022). A review of safe reinforcement learning: Methods, theory and applications. arXiv preprint arXiv:2205.10330"},{"key":"9669_CR46","doi-asserted-by":"publisher","first-page":"103360","DOI":"10.1016\/j.engappai.2019.103360","volume":"88","author":"J Garc\u00eda","year":"2020","unstructured":"Garc\u00eda, J., & Shafie, D. (2020). Teaching a humanoid robot to walk faster through safe reinforcement learning. Engineering Applications of Artificial Intelligence, 88, 103360.","journal-title":"Engineering Applications of Artificial Intelligence"}],"container-title":["Autonomous Agents and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-024-09669-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10458-024-09669-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-024-09669-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T10:22:38Z","timestamp":1731493358000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10458-024-09669-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,6]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["9669"],"URL":"https:\/\/doi.org\/10.1007\/s10458-024-09669-2","relation":{},"ISSN":["1387-2532","1573-7454"],"issn-type":[{"value":"1387-2532","type":"print"},{"value":"1573-7454","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,6]]},"assertion":[{"value":"24 July 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 August 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"38"}}