{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T07:06:54Z","timestamp":1780384014671,"version":"3.54.1"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031539688","type":"print"},{"value":"9783031539695","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-53969-5_7","type":"book-chapter","created":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T09:03:35Z","timestamp":1707987815000},"page":"78-92","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["ContainerGym: A Real-World Reinforcement Learning Benchmark for\u00a0Resource Allocation"],"prefix":"10.1007","author":[{"given":"Abhijeet","family":"Pendyala","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Justin","family":"Dettmer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Glasmachers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Asma","family":"Atamna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,2,16]]},"reference":[{"key":"7_CR1","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"MG Bellemare","year":"2013","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253\u2013279 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"7_CR2","unstructured":"Brockman, G., et al.: Openai gym (2016)"},{"issue":"9\u201312","key":"7_CR3","doi-asserted-by":"publisher","first-page":"2981","DOI":"10.1007\/s00170-018-2690-6","volume":"99","author":"M Compare","year":"2018","unstructured":"Compare, M., Bellani, L., Cobelli, E., Zio, E.: Reinforcement learning-based flow management of gas turbine parts under stochastic failures. Int. J. Adv. Manuf. Technol. 99(9\u201312), 2981\u20132992 (2018)","journal-title":"Int. J. Adv. Manuf. Technol."},{"issue":"7897","key":"7_CR4","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1038\/s41586-021-04301-9","volume":"602","author":"J Degrave","year":"2022","unstructured":"Degrave, J., et al.: Magnetic control of tokamak plasmas through deep reinforcement learning. Nature 602(7897), 414\u2013419 (2022)","journal-title":"Nature"},{"key":"7_CR5","unstructured":"Dulac-Arnold, G., et al.: An empirical investigation of the challenges of real-world reinforcement learning. CoRR arxiv:2003.11881 (2020)"},{"key":"7_CR6","unstructured":"Haarnoja, T., et al.: Soft actor-critic algorithms and applications. CoRR arxiv:1812.05905 (2018)"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Hein, D., et al.: A benchmark environment motivated by industrial control problems. In: 2017 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE (2017)","DOI":"10.1109\/SSCI.2017.8280935"},{"key":"7_CR8","unstructured":"Lazic, N., et al.: Data center cooling using model-predictive control. In: Proceedings of the Thirty-Second Conference on Neural Information Processing Systems (NeurIPS-2018), Montreal, QC, pp. 3818\u20133827 (2018)"},{"key":"7_CR9","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. CoRR arxiv:1312.5602 (2013)"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Osi\u0144ski, B., et al.: Simulation-based reinforcement learning for real-world autonomous driving. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 6411\u20136418 (2020)","DOI":"10.1109\/ICRA40945.2020.9196730"},{"issue":"268","key":"7_CR11","first-page":"1","volume":"22","author":"A Raffin","year":"2021","unstructured":"Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., Dormann, N.: Stable-baselines3: reliable reinforcement learning implementations. J. Mach. Learn. Res. 22(268), 1\u20138 (2021)","journal-title":"J. Mach. Learn. Res."},{"key":"7_CR12","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: Bach, F., Blei, D. (eds.) Proceedings of the 32nd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 37, pp. 1889\u20131897. PMLR (2015)"},{"key":"7_CR13","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. CoRR arxiv:1707.06347 (2017)"},{"issue":"7587","key":"7_CR14","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)","journal-title":"Nature"},{"key":"7_CR15","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT press, Cambridge (2018)"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: Mujoco: a physics engine for model-based control. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5026\u20135033 (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"issue":"7782","key":"7_CR17","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., et al.: Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","journal-title":"Nature"}],"container-title":["Lecture Notes in Computer Science","Machine Learning, Optimization, and Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53969-5_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T09:05:03Z","timestamp":1707987903000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53969-5_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031539688","9783031539695"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53969-5_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"16 February 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"LOD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Machine Learning, Optimization, and Data Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Grasmere","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mod2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/lod2023.icas.cc\/","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":"In-house system and EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"119","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":"72","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":"61% - 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":"5-6","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":"1-2","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)"}}]}}