{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T18:03:33Z","timestamp":1779991413446,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,29]]},"DOI":"10.1145\/3774905.3795854","type":"proceedings-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T17:14:56Z","timestamp":1779988496000},"page":"1453-1460","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Boltzmann Interaction Models with Gibbs Decision Policies in Multi-Agent Delivery Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9686-8493","authenticated-orcid":false,"given":"Vitaly A.","family":"Krasikov","sequence":"first","affiliation":[{"name":"Bauman Moscow State Technical University, Moscow, Russian Federation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8986-402X","authenticated-orcid":false,"given":"Ivan P.","family":"Malashin","sequence":"additional","affiliation":[{"name":"Bauman Moscow State Technical University, Moscow, Russian Federation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9648-2395","authenticated-orcid":false,"given":"Aleksei S.","family":"Borodulin","sequence":"additional","affiliation":[{"name":"Bauman Moscow State Technical University, Moscow, Russian Federation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4246-9742","authenticated-orcid":false,"given":"Andrei P.","family":"Gantimurov","sequence":"additional","affiliation":[{"name":"Bauman Moscow State Technical University, Moscow, Russian Federation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1563-4036","authenticated-orcid":false,"given":"Dmitry A.","family":"Martysyuk","sequence":"additional","affiliation":[{"name":"Bauman Moscow State Technical University, Moscow, Russian Federation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4263-2367","authenticated-orcid":false,"given":"Vladimir A.","family":"Nelyub","sequence":"additional","affiliation":[{"name":"Bauman Moscow State Technical University, Moscow, Russian Federation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3997-342X","authenticated-orcid":false,"given":"Igor S.","family":"Masich","sequence":"additional","affiliation":[{"name":"Bauman Moscow State Technical University, Moscow, Russian Federation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3959-2969","authenticated-orcid":false,"given":"Vadim S.","family":"Tynchneko","sequence":"additional","affiliation":[{"name":"Bauman Moscow State Technical University, Moscow, Russian Federation"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,5,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3508033"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.3390\/aerospace12030265"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12450"},{"key":"e_1_3_2_1_4_1","volume-title":"Reinforcement learning using quantum Boltzmann machines. arXiv preprint arXiv:1612.05695","author":"Crawford Daniel","year":"2016","unstructured":"Daniel Crawford, Anna Levit, Navid Ghadermarzy, Jaspreet S Oberoi, and Pooya Ronagh. 2016. Reinforcement learning using quantum Boltzmann machines. arXiv preprint arXiv:1612.05695 (2016)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3323704"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128370"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3075202"},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 289-297","author":"Huang Jiawei","year":"2024","unstructured":"Jiawei Huang, Batuhan Yardim, and Niao He. 2024. On the statistical efficiency of mean-field reinforcement learning with general function approximation. In International Conference on Artificial Intelligence and Statistics. PMLR, 289-297."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3265"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/QCE60285.2024.10298"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2025.117243"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.3390\/sym17091382"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3515814"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1142\/0271"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.applthermaleng.2023.121919"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0370-1573(00)00120-4"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1088\/2058-9565\/ad261b"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120495"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3329513"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12083-024-01829-1"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i26.34977"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3730848"},{"key":"e_1_3_2_1_23_1","volume-title":"MAXINFORL: BOOSTING EXPLORATION IN REINFORCEMENT LEARNING THROUGH INFORMATION GAIN MAXIMIZATION. International Conference on Learning Representations, ICLR, 73223 - 73251","author":"Sukhija Bhavya","year":"2025","unstructured":"Bhavya Sukhija, Stelian Coros, Andreas Krause, Pieter Abbeel, and Carmelo Sferrazza. 2025. MAXINFORL: BOOSTING EXPLORATION IN REINFORCEMENT LEARNING THROUGH INFORMATION GAIN MAXIMIZATION. International Conference on Learning Representations, ICLR, 73223 - 73251. https:\/\/www.scopus.com\/inward\/record.uri?eid=2-s2.0-105010259801&partnerID=40&md5=6b2a4982dd9c4a7ae1fca2506e3e934c"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.3390\/drones9070512"},{"key":"e_1_3_2_1_25_1","volume-title":"International conference on machine learning. PMLR, 5571-5580","author":"Yang Yaodong","year":"2018","unstructured":"Yaodong Yang, Rui Luo, Minne Li, Ming Zhou, Weinan Zhang, and Jun Wang. 2018. Mean field multi-agent reinforcement learning. In International conference on machine learning. PMLR, 5571-5580."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111663"},{"key":"e_1_3_2_1_27_1","volume-title":"Multi-agent reinforcement learning: A selective overview of theories and algorithms. Handbook of reinforcement learning and control","author":"Zhang Kaiqing","year":"2021","unstructured":"Kaiqing Zhang, Zhuoran Yang, and Tamer Ba\u015far. 2021. Multi-agent reinforcement learning: A selective overview of theories and algorithms. Handbook of reinforcement learning and control (2021), 321-384."},{"key":"e_1_3_2_1_28_1","volume-title":"Discretizing Continuous Action Space With Unimodal Probability Distributions for On-Policy Reinforcement Learning","author":"Zhu Yuanyang","year":"2024","unstructured":"Yuanyang Zhu, Zhi Wang, Yuanheng Zhu, Chunlin Chen, and Dongbin Zhao. 2024. Discretizing Continuous Action Space With Unimodal Probability Distributions for On-Policy Reinforcement Learning. IEEE Transactions on Neural Networks and Learning Systems (2024)."}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774905.3795854","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T17:17:46Z","timestamp":1779988666000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774905.3795854"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,28]]},"references-count":28,"alternative-id":["10.1145\/3774905.3795854","10.1145\/3774905"],"URL":"https:\/\/doi.org\/10.1145\/3774905.3795854","relation":{},"subject":[],"published":{"date-parts":[[2026,5,28]]},"assertion":[{"value":"2026-05-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}