{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T22:44:02Z","timestamp":1743029042964,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031353604"},{"type":"electronic","value":"9783031353611"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-35361-1_3","type":"book-chapter","created":{"date-parts":[[2023,6,14]],"date-time":"2023-06-14T14:04:07Z","timestamp":1686751447000},"page":"52-70","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ScaRLib: A Framework for\u00a0Cooperative Many Agent Deep Reinforcement Learning in\u00a0Scala"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8337-8990","authenticated-orcid":false,"given":"Davide","family":"Domini","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4050-9989","authenticated-orcid":false,"given":"Filippo","family":"Cavallari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1553-4561","authenticated-orcid":false,"given":"Gianluca","family":"Aguzzi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2702-5702","authenticated-orcid":false,"given":"Mirko","family":"Viroli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,6,15]]},"reference":[{"key":"3_CR1","doi-asserted-by":"publisher","unstructured":"Aguzzi, G.: Research directions for aggregate computing with machine learning. In: 2021 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C). IEEE (2021). https:\/\/doi.org\/10.1109\/acsos-c52956.2021.00078","DOI":"10.1109\/acsos-c52956.2021.00078"},{"key":"3_CR2","doi-asserted-by":"publisher","unstructured":"Aguzzi, G., Casadei, R., Pianini, D., Viroli, M.: Dynamic decentralization domains for the internet of things. IEEE Internet Comput. 26(6), 16\u201323 (2022). https:\/\/doi.org\/10.1109\/mic.2022.3216753","DOI":"10.1109\/mic.2022.3216753"},{"key":"3_CR3","doi-asserted-by":"publisher","unstructured":"Aguzzi, G., Casadei, R., Viroli, M.: Addressing collective computations efficiency: Towards a platform-level reinforcement learning approach. In: Casadei, R., et al. (eds.) IEEE International Conference on Autonomic Computing and Self-Organizing Systems, ACSOS 2022, Virtual, CA, USA, 19\u201323 September 2022, pp. 11\u201320. IEEE (2022). https:\/\/doi.org\/10.1109\/ACSOS55765.2022.00019","DOI":"10.1109\/ACSOS55765.2022.00019"},{"key":"3_CR4","doi-asserted-by":"publisher","unstructured":"Aguzzi, G., Casadei, R., Viroli, M.: Machine learning for aggregate computing: a research roadmap. In: 2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops (ICDCSW). IEEE (2022). https:\/\/doi.org\/10.1109\/icdcsw56584.2022.00032","DOI":"10.1109\/icdcsw56584.2022.00032"},{"key":"3_CR5","doi-asserted-by":"publisher","unstructured":"Aguzzi, G., Casadei, R., Viroli, M.: Towards reinforcement learning-based aggregate computing. In: ter Beek, M.H., Sirjani, M. (eds) Coordination Models and Languages. COORDINATION 2022. IFIP Advances in Information and Communication Technology, vol. 13271, pp. 72\u201391. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-08143-9_5","DOI":"10.1007\/978-3-031-08143-9_5"},{"key":"3_CR6","doi-asserted-by":"publisher","unstructured":"Baker, B., et al.: Emergent tool use from multi-agent autocurricula (2019). https:\/\/doi.org\/10.48550\/ARXIV.1909.07528. https:\/\/arxiv.org\/abs\/1909.07528","DOI":"10.48550\/ARXIV.1909.07528"},{"key":"3_CR7","doi-asserted-by":"publisher","unstructured":"Beal, J., Pianini, D., Viroli, M.: Aggregate programming for the internet of things. Computer 48(9), 22\u201330 (2015). https:\/\/doi.org\/10.1109\/mc.2015.261","DOI":"10.1109\/mc.2015.261"},{"key":"3_CR8","unstructured":"Bettini, M., Kortvelesy, R., Blumenkamp, J., Prorok, A.: VMAS: a vectorized multi-agent simulator for collective robot learning. The 16th International Symposium on Distributed Autonomous Robotic Systems (2022)"},{"key":"3_CR9","doi-asserted-by":"publisher","unstructured":"Busoniu, L., Babuska, R., Schutter, B.D.: A comprehensive survey of multiagent reinforcement learning. IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.) 38(2), 156\u2013172 (2008). https:\/\/doi.org\/10.1109\/tsmcc.2007.913919","DOI":"10.1109\/tsmcc.2007.913919"},{"key":"3_CR10","doi-asserted-by":"publisher","unstructured":"Casadei, R.: Macroprogramming: Concepts, state of the art, and opportunities of macroscopic behaviour modelling. ACM Computing Surveys (2023). https:\/\/doi.org\/10.1145\/3579353","DOI":"10.1145\/3579353"},{"key":"3_CR11","doi-asserted-by":"publisher","unstructured":"Casadei, R., Viroli, M., Aguzzi, G., Pianini, D.: ScaFi: a scala DSL and toolkit for aggregate programming. SoftwareX 20, 101248 (2022). https:\/\/doi.org\/10.1016\/j.softx.2022.101248","DOI":"10.1016\/j.softx.2022.101248"},{"key":"3_CR12","doi-asserted-by":"publisher","unstructured":"Casadei, R., Viroli, M., Audrito, G., Pianini, D., Damiani, F.: Engineering collective intelligence at the edge with aggregate processes. Eng. Appl. Artif. Intell. 97, 104081 (2021). https:\/\/doi.org\/10.1016\/j.engappai.2020.104081","DOI":"10.1016\/j.engappai.2020.104081"},{"key":"3_CR13","doi-asserted-by":"publisher","unstructured":"Chu, T., Wang, J., Codec\u00e0, L., Li, Z.: Multi-agent deep reinforcement learning for large-scale traffic signal control (2019). https:\/\/doi.org\/10.48550\/ARXIV.1903.04527. https:\/\/arxiv.org\/abs\/1903.04527","DOI":"10.48550\/ARXIV.1903.04527"},{"issue":"5","key":"3_CR14","doi-asserted-by":"publisher","first-page":"3215","DOI":"10.1007\/s10462-020-09938-y","volume":"54","author":"W Du","year":"2020","unstructured":"Du, W., Ding, S.: A survey on multi-agent deep reinforcement learning: from the perspective of challenges and applications. Artif. Intell. Rev. 54(5), 3215\u20133238 (2020). https:\/\/doi.org\/10.1007\/s10462-020-09938-y","journal-title":"Artif. Intell. Rev."},{"key":"3_CR15","unstructured":"Fey, M., Lenssen, J.E.: Fast graph representation learning with pyTorch geometric (2019)"},{"key":"3_CR16","doi-asserted-by":"publisher","unstructured":"He, K., Doshi, P., Banerjee, B.: Many agent reinforcement learning under partial observability (2021). https:\/\/doi.org\/10.48550\/ARXIV.2106.09825. https:\/\/arxiv.org\/abs\/2106.09825","DOI":"10.48550\/ARXIV.2106.09825"},{"issue":"54","key":"3_CR17","first-page":"1","volume":"20","author":"M H\u00fcttenrauch","year":"2019","unstructured":"H\u00fcttenrauch, M., Adrian, S., Neumann, G., et al.: Deep reinforcement learning for swarm systems. J. Mach. Learn. Res. 20(54), 1\u201331 (2019)","journal-title":"J. Mach. Learn. Res."},{"key":"3_CR18","doi-asserted-by":"publisher","unstructured":"Laddad, S., Sen, K.: ScalaPy: seamless python interoperability for cross-platform scala programs. In: Proceedings of the 11th ACM SIGPLAN International Symposium on Scala. ACM (2020). https:\/\/doi.org\/10.1145\/3426426.3428485","DOI":"10.1145\/3426426.3428485"},{"key":"3_CR19","doi-asserted-by":"publisher","unstructured":"Lei, L., Tan, Y., Zheng, K., Liu, S., Zhang, K., Shen, X.: Deep reinforcement learning for autonomous internet of things: Model, applications and challenges. IEEE Commun. Surv. Tutorials 22(3), 1722\u20131760 (2020). https:\/\/doi.org\/10.1109\/comst.2020.2988367","DOI":"10.1109\/comst.2020.2988367"},{"key":"3_CR20","doi-asserted-by":"publisher","unstructured":"Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: Cohen, W.W., Hirsh, H. (eds.) Machine Learning Proceedings 1994, pp. 157\u2013163. Morgan Kaufmann, San Francisco (CA) (1994). https:\/\/doi.org\/10.1016\/B978-1-55860-335-6.50027-1. https:\/\/www.sciencedirect.com\/science\/article\/pii\/B9781558603356500271","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"3_CR21","doi-asserted-by":"publisher","unstructured":"Long, P., Fanl, T., Liao, X., Liu, W., Zhang, H., Pan, J.: Towards optimally decentralized multi-robot collision avoidance via deep reinforcement learning. In: 2018 IEEE International Conference on Robotics and Automation (ICRA). IEEE (2018). https:\/\/doi.org\/10.1109\/icra.2018.8461113","DOI":"10.1109\/icra.2018.8461113"},{"key":"3_CR22","doi-asserted-by":"publisher","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning (2013). https:\/\/doi.org\/10.48550\/ARXIV.1312.5602. https:\/\/arxiv.org\/abs\/1312.5602","DOI":"10.48550\/ARXIV.1312.5602"},{"key":"3_CR23","doi-asserted-by":"publisher","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015). https:\/\/doi.org\/10.1038\/nature14236","DOI":"10.1038\/nature14236"},{"key":"3_CR24","doi-asserted-by":"publisher","unstructured":"Moritz, P., et al.: Ray: a distributed framework for emerging AI applications (2017). https:\/\/doi.org\/10.48550\/ARXIV.1712.05889. https:\/\/arxiv.org\/abs\/1712.05889","DOI":"10.48550\/ARXIV.1712.05889"},{"key":"3_CR25","doi-asserted-by":"publisher","unstructured":"Pianini, D., Montagna, S., Viroli, M.: Chemical-oriented simulation of computational systems with ALCHEMIST. J. Simulation 7(3), 202\u2013215 (2013). https:\/\/doi.org\/10.1057\/jos.2012.27","DOI":"10.1057\/jos.2012.27"},{"key":"3_CR26","doi-asserted-by":"publisher","unstructured":"Reynolds, C.W.: Flocks, herds and schools: a distributed behavioral model. In: Stone, M.C. (ed.) Proceedings of the 14th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1987, Anaheim, California, USA, 27\u201331 July 1987, pp. 25\u201334. ACM (1987). https:\/\/doi.org\/10.1145\/37401.37406","DOI":"10.1145\/37401.37406"},{"key":"3_CR27","unstructured":"Richmond, P., Coakley, S., Romano, D.M.: A high performance agent based modelling framework on graphics card hardware with Cuda. In: Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems - Volume 2, pp. 1125\u20131126. AAMAS 2009, International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC (2009)"},{"key":"3_CR28","doi-asserted-by":"publisher","unstructured":"Samvelyan, M., et al.: The starcraft multi-agent challenge (2019). https:\/\/doi.org\/10.48550\/ARXIV.1902.04043. https:\/\/arxiv.org\/abs\/1902.04043","DOI":"10.48550\/ARXIV.1902.04043"},{"key":"3_CR29","unstructured":"Samvelyan, M., et al.: The StarCraft Multi-Agent Challenge. CoRR abs\/1902.04043 (2019)"},{"key":"3_CR30","doi-asserted-by":"publisher","unstructured":"Suarez, J., Du, Y., Isola, P., Mordatch, I.: Neural MMO: a massively multiagent game environment for training and evaluating intelligent agents (2019). https:\/\/doi.org\/10.48550\/ARXIV.1903.00784. https:\/\/arxiv.org\/abs\/1903.00784","DOI":"10.48550\/ARXIV.1903.00784"},{"key":"3_CR31","unstructured":"Terry, J., et al.: PettingZoo: Gym for multi-agent reinforcement learning. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems. vol. 34, pp. 15032\u201315043. Curran Associates, Inc. (2021). https:\/\/proceedings.neurips.cc\/paper\/2021\/file\/7ed2d3454c5eea71148b11d0c25104ff-Paper.pdf"},{"key":"3_CR32","doi-asserted-by":"publisher","unstructured":"Watkins, C.J.C.H., Dayan, P.: Q-learning. Mach. Learn. 8(3-4), 279\u2013292 (1992). https:\/\/doi.org\/10.1007\/bf00992698","DOI":"10.1007\/bf00992698"},{"key":"3_CR33","unstructured":"Yang, Y.: Many-agent reinforcement learning, Ph. D. thesis, UCL (University College London) (2021)"},{"key":"3_CR34","doi-asserted-by":"publisher","unstructured":"Yang, Y., Luo, R., Li, M., Zhou, M., Zhang, W., Wang, J.: Mean field multi-agent reinforcement learning (2018). https:\/\/doi.org\/10.48550\/ARXIV.1802.05438. https:\/\/arxiv.org\/abs\/1802.05438","DOI":"10.48550\/ARXIV.1802.05438"},{"key":"3_CR35","doi-asserted-by":"publisher","unstructured":"Yu, C., et al.: The surprising effectiveness of PPO in cooperative, multi-agent games (2021). https:\/\/doi.org\/10.48550\/ARXIV.2103.01955. https:\/\/arxiv.org\/abs\/2103.01955","DOI":"10.48550\/ARXIV.2103.01955"},{"key":"3_CR36","doi-asserted-by":"publisher","unstructured":"\u0160o\u0161i\u0107, A., KhudaBukhsh, W.R., Zoubir, A.M., Koeppl, H.: Inverse reinforcement learning in swarm systems (2016). https:\/\/doi.org\/10.48550\/ARXIV.1602.05450. https:\/\/arxiv.org\/abs\/1602.05450","DOI":"10.48550\/ARXIV.1602.05450"}],"container-title":["Lecture Notes in Computer Science","Coordination Models and Languages"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-35361-1_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,14]],"date-time":"2023-06-14T14:04:58Z","timestamp":1686751498000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-35361-1_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031353604","9783031353611"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-35361-1_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"15 June 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"COORDINATION","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Coordination Languages and Models","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lisbon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","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":"19 June 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 June 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"coordination2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.discotec.org\/2023\/coordination","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27","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":"12","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":"2","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":"44% - 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)"}}]}}