{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T00:42:05Z","timestamp":1743122525573,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031703775"},{"type":"electronic","value":"9783031703782"}],"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\/978-3-031-70378-2_3","type":"book-chapter","created":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T09:02:05Z","timestamp":1725181325000},"page":"38-54","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PeersimGym: An Environment for\u00a0Solving the\u00a0Task Offloading Problem with\u00a0Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Frederico","family":"Metelo","sequence":"first","affiliation":[]},{"given":"Cl\u00e1udia","family":"Soares","sequence":"additional","affiliation":[]},{"given":"Stevo","family":"Rackovi\u0107","sequence":"additional","affiliation":[]},{"given":"Pedro \u00c1kos","family":"Costa","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,22]]},"reference":[{"key":"3_CR1","volume-title":"Introduction to Telecommunications Network Engineering","author":"T Anttalainen","year":"2003","unstructured":"Anttalainen, T.: Introduction to Telecommunications Network Engineering, 2nd edn. Artech House Telecommunications Library. Artech House, Boston (2003)","edition":"2"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Baek, J., et al.: Managing fog networks using reinforcement learning based load balancing algorithm. In: 2019 IEEE WCNC, pp. 1\u20137 (2019)","DOI":"10.1109\/WCNC.2019.8885745"},{"key":"3_CR3","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1109\/TNSM.2022.3210827","volume":"20","author":"J Baek","year":"2023","unstructured":"Baek, J., Kaddoum, G.: FLoadNet: load balancing in fog networks with cooperative multiagent using actor-critic method. IEEE Trans. Netw. Serv. Manag. 20, 400\u2013414 (2023)","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"issue":"5","key":"3_CR4","doi-asserted-by":"publisher","first-page":"1999","DOI":"10.1007\/s11280-022-01011-8","volume":"25","author":"F Dai","year":"2022","unstructured":"Dai, F., et al.: Task offloading for vehicular edge computing with edge-cloud cooperation. World Wide Web 25(5), 1999\u20132017 (2022)","journal-title":"World Wide Web"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Gaw\u0142owicz, P., Zubow, A.: ns-3 meets OpenAI gym: the playground for machine learning in networking research. In: ACM International Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems (2019)","DOI":"10.1145\/3345768.3355908"},{"key":"3_CR6","doi-asserted-by":"publisher","first-page":"12416","DOI":"10.1109\/JIOT.2023.3247013","volume":"10","author":"L Geng","year":"2023","unstructured":"Geng, L., et al.: Deep reinforcement learning based distributed computation offloading in vehicular edge computing networks. IEEE Internet Things J. 10, 12416\u201312433 (2023)","journal-title":"IEEE Internet Things J."},{"issue":"6","key":"3_CR7","doi-asserted-by":"publisher","first-page":"3870","DOI":"10.1109\/TNSE.2021.3115054","volume":"9","author":"H Huang","year":"2021","unstructured":"Huang, H., Ye, Q., Zhou, Y.: Deadline-aware task offloading with partially-observable deep reinforcement learning for multi-access edge computing. IEEE Trans. Netw. Sci. Eng. 9(6), 3870\u20133885 (2021)","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"issue":"1","key":"3_CR8","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1007\/s10922-022-09696-y","volume":"31","author":"V Jain","year":"2023","unstructured":"Jain, V., Kumar, B.: QoS-aware task offloading in fog environment using multiagent deep reinforcement learning. J. Netw. Syst. Manag. 31(1), 7 (2023)","journal-title":"J. Netw. Syst. Manag."},{"issue":"1","key":"3_CR9","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1007\/s12083-022-01348-x","volume":"16","author":"L Lin","year":"2023","unstructured":"Lin, L., Zhou, W., Yang, Z., Liu, J.: Deep reinforcement learning-based task scheduling and resource allocation for NOMA-MEC in Industrial Internet of Things. Peer-to-Peer Network. Appl. 16(1), 170\u2013188 (2023)","journal-title":"Peer-to-Peer Network. Appl."},{"issue":"11","key":"3_CR10","doi-asserted-by":"publisher","first-page":"11158","DOI":"10.1109\/TVT.2019.2935450","volume":"68","author":"Y Liu","year":"2019","unstructured":"Liu, Y., Yu, H., Xie, S., Zhang, Y.: Deep reinforcement learning for offloading and resource allocation in vehicle edge computing and networks. IEEE Trans. Veh. Technol. 68(11), 11158\u201311168 (2019)","journal-title":"IEEE Trans. Veh. Technol."},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Mahmud, M.R., Pallewatta, S., Goudarzi, M., Buyya, R.: IFogSim2: an extended iFogSim simulator for mobility, clustering, and microservice management in edge and fog computing environments. CoRR arxiv:2109.05636 (2021)","DOI":"10.1016\/j.jss.2022.111351"},{"issue":"2","key":"3_CR12","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1109\/TVT.2018.2890685","volume":"68","author":"M Min","year":"2019","unstructured":"Min, M., et al.: Learning-based computation offloading for IoT devices with energy harvesting. IEEE Trans. Veh. Technol. 68(2), 1930\u20131941 (2019)","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"7540","key":"3_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)","journal-title":"Nature"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Montresor, A., Jelasity, M.: PeerSim: a scalable P2P simulator. In: Proceedings of the 9th International Conference on Peer-to-Peer, Seattle, WA, pp. 99\u2013100 (2009)","DOI":"10.1109\/P2P.2009.5284506"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Muniswamaiah, M., Agerwala, T., Tappert, C.C.: A survey on cloudlets, mobile edge, and fog computing. In: 8th IEEE CSCloud\/7th IEEE EdgeCom (2021)","DOI":"10.1109\/CSCloud-EdgeCom52276.2021.00034"},{"key":"3_CR16","unstructured":"Ng, A.Y., Harada, D., Russell, S.: Policy invariance under reward transformations: theory and application to reward shaping. In: ICML, pp. 278\u2013287 (1999)"},{"key":"3_CR17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_14","volume-title":"Game Theory and Multi-agent Reinforcement Learning","author":"A Now\u00e9","year":"2012","unstructured":"Now\u00e9, A., Vrancx, P., De Hauwere, Y.M.: Game Theory and Multi-agent Reinforcement Learning. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-27645-3_14"},{"key":"3_CR18","doi-asserted-by":"publisher","first-page":"2089","DOI":"10.1109\/JSYST.2022.3190926","volume":"17","author":"X Peng","year":"2022","unstructured":"Peng, X., et al.: Deep reinforcement learning for shared offloading strategy in vehicle edge computing. IEEE Syst. J. 17, 2089\u20132100 (2022)","journal-title":"IEEE Syst. J."},{"issue":"8","key":"3_CR19","doi-asserted-by":"publisher","first-page":"8050","DOI":"10.1109\/TVT.2019.2924015","volume":"68","author":"X Qiu","year":"2019","unstructured":"Qiu, X., et al.: Online deep reinforcement learning for computation offloading in blockchain-empowered mobile edge computing. IEEE Trans. Veh. Technol. 68(8), 8050\u20138062 (2019)","journal-title":"IEEE Trans. Veh. Technol."},{"key":"3_CR20","unstructured":"Rausch, T, et al.: Synthesizing plausible infrastructure configurations for evaluating edge computing systems. In: 3rd USENIX Workshop HotEdge 2020 (2020)"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Santos, J., Wauters, T., Volckaert, B., De Turck, F.: Reinforcement learning for service function chain allocation in fog computing. In: Book Chapter in revision, Submitted to Communications Network and Service Management in the Era of Artificial Intelligence and Machine Learning, IEEE Press (2020)","DOI":"10.1002\/9781119675525.ch7"},{"issue":"11","key":"3_CR22","doi-asserted-by":"publisher","DOI":"10.1002\/ett.3493","volume":"29","author":"C Sonmez","year":"2018","unstructured":"Sonmez, C., Ozgovde, A., Ersoy, C.: Edgecloudsim: an environment for performance evaluation of edge computing systems. Trans. Emerg. Telecommun. Technol. 29(11), e3493 (2018)","journal-title":"Trans. Emerg. Telecommun. Technol."},{"key":"3_CR23","unstructured":"Terry, J.K., et al.: PettingZoo: gym for multi-agent reinforcement learning. CoRR arxiv:2009.14471 (2020)"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Tian, H., Zheng, Y., Wang, W.: Characterizing and synthesizing task dependencies of data-parallel jobs in alibaba cloud. In: Proceedings of ACM Symposium Cloud Computing (2019)","DOI":"10.1145\/3357223.3362710"},{"key":"3_CR25","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1016\/j.future.2023.04.004","volume":"145","author":"Z Tong","year":"2023","unstructured":"Tong, Z., et al.: Multi-type task offloading for wireless Internet of Things by federated deep reinforcement learning. Futur. Gener. Comput. Syst. 145, 536\u2013549 (2023)","journal-title":"Futur. Gener. Comput. Syst."},{"key":"3_CR26","unstructured":"Towers, M., et al.: Gymnasium (2023)"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Van Le, D., Tham, C.K.: A deep reinforcement learning based offloading scheme in ad-hoc mobile clouds. In: IEEE Infocom Workshops, pp. 760\u2013765 (2018)","DOI":"10.1109\/INFCOMW.2018.8406881"},{"key":"3_CR28","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1016\/j.future.2017.09.020","volume":"79","author":"B Varghese","year":"2018","unstructured":"Varghese, B., Buyya, R.: Next generation cloud computing: new trends and research directions. Futur. Gener. Comput. Syst. 79, 849\u2013861 (2018)","journal-title":"Futur. Gener. Comput. Syst."},{"issue":"4","key":"3_CR29","doi-asserted-by":"publisher","first-page":"2238","DOI":"10.1109\/JIOT.2020.3026589","volume":"8","author":"S Yu","year":"2020","unstructured":"Yu, S., et al.: When deep reinforcement learning meets federated learning: intelligent multitimescale resource management for multiaccess edge computing in 5G ultradense network. IEEE Internet Things J. 8(4), 2238\u20132251 (2020)","journal-title":"IEEE Internet Things J."},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, F., et al.: Cooperative partial task offloading and resource allocation for IIoT based on decentralized multi-agent deep reinforcement learning. IEEE Internet Things J. (2023)","DOI":"10.1109\/VTC2023-Fall60731.2023.10333859"},{"key":"3_CR31","doi-asserted-by":"publisher","first-page":"2636","DOI":"10.1109\/TPDS.2019.2927978","volume":"30","author":"Z Zhu","year":"2019","unstructured":"Zhu, Z., Liu, T., Yang, Y., Luo, X.: BLOT: bandit learning-based offloading of tasks in fog-enabled networks. IEEE Trans. Parallel Distrib. Syst. 30, 2636\u20132649 (2019)","journal-title":"IEEE Trans. Parallel Distrib. Syst."}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70378-2_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T09:02:50Z","timestamp":1725181370000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70378-2_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031703775","9783031703782"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70378-2_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"22 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vilnius","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}