{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:26:09Z","timestamp":1750220769416,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,2,27]],"date-time":"2020-02-27T00:00:00Z","timestamp":1582761600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,2,27]]},"DOI":"10.1145\/3385032.3385041","type":"proceedings-article","created":{"date-parts":[[2020,3,25]],"date-time":"2020-03-25T10:04:52Z","timestamp":1585130692000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Language Support for Multi Agent Reinforcement Learning"],"prefix":"10.1145","author":[{"given":"Tony","family":"Clark","sequence":"first","affiliation":[{"name":"Aston University, Birmingham, UK"}]},{"given":"Balbir","family":"Barn","sequence":"additional","affiliation":[{"name":"Middlesex University, London, UK"}]},{"given":"Vinay","family":"Kulkarni","sequence":"additional","affiliation":[{"name":"TCS Research, Pune, India"}]},{"given":"Souvik","family":"Barat","sequence":"additional","affiliation":[{"name":"TCS Research, Pune, India"}]}],"member":"320","published-online":{"date-parts":[[2020,3,25]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2017.03.001"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0084816"},{"key":"e_1_3_2_1_3_1","first-page":"1019","volume-title":"Advances in neural information processing systems","author":"Andre David","year":"2001","unstructured":"David Andre and Stuart J Russell. Programmable reinforcement learning agents. In Advances in neural information processing systems, pages 1019--1025, 2001."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CSCS.2015.71"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/SYNASC.2017.00065"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70241-4"},{"key":"e_1_3_2_1_7_1","first-page":"61","volume-title":"Proceedings of the 2017 Winter Simulation Conference","author":"Barat Souvik","unstructured":"Souvik Barat, Vinay Kulkarni, Tony Clark, and Balbir Barn. An actor-model based bottom-up simulation: an experiment on indian demonetisation initiative. In Proceedings of the 2017 Winter Simulation Conference, page 61. IEEE Press, 2017."},{"key":"e_1_3_2_1_8_1","volume-title":"The European Simulation and Modelling Conference, ESM 2017","author":"Barat Souvik","year":"2017","unstructured":"Souvik Barat, Vinay Kulkarni, Tony Clark, and Balbir Barn. A domain-specific language for complex dynamic decision making. In The European Simulation and Modelling Conference, ESM 2017, Lisbon, Portugal, October 25-27, 2017, 2017."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/3306127.3331924"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4818"},{"key":"e_1_3_2_1_11_1","volume-title":"Jorge J Gomez-Sanz, Joao Leite, Gregory O'Hare, Alexander Pokahr, and Alessandro Ricci. A survey of programming languages and platforms for multi-agent systems. Informatica, 30(1)","author":"Bordini Rafael H","year":"2006","unstructured":"Rafael H Bordini, Lars Braubach, Mehdi Dastani, A El F Seghrouchni, Jorge J Gomez-Sanz, Joao Leite, Gregory O'Hare, Alexander Pokahr, and Alessandro Ricci. A survey of programming languages and platforms for multi-agent systems. Informatica, 30(1), 2006."},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of TMCE, Las Palmas de Gran Canaria, Spain Edited by: Horvath I., Suarez Rivero JP and Hernandez Castellano PM","author":"Boschert Stefan","year":"2018","unstructured":"Stefan Boschert, Christoph Heinrich, and Roland Rosen. Next generation digital twin. Proceedings of TMCE, Las Palmas de Gran Canaria, Spain Edited by: Horvath I., Suarez Rivero JP and Hernandez Castellano PM, 2018."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2008.03.007"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1007\/978-3-319-45748-2_36","volume-title":"Engineering Systems and Networks","author":"Costas Jos\u00e9","year":"2017","unstructured":"Jos\u00e9 Costas, Borja Ponte, David de la Fuente, Jes\u00fas Lozano, and Jos\u00e9 Parre\u00f1o. Agents playing the beer distribution game: Solving the dilemma through the drum-buffer-rope methodology. In Engineering Systems and Networks, pages 337--345. Springer, 2017."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMAS.1998.699041"},{"key":"e_1_3_2_1_17_1","first-page":"2137","volume-title":"Advances in Neural Information Processing Systems","author":"Foerster Jakob","year":"2016","unstructured":"Jakob Foerster, Ioannis Alexandros Assael, Nando de Freitas, and Shimon Whiteson. Learning to communicate with deep multi-agent reinforcement learning. In Advances in Neural Information Processing Systems, pages 2137--2145, 2016."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpat.2017.11.007"},{"key":"e_1_3_2_1_19_1","first-page":"1","volume-title":"Digital twin: Manufacturing excellence through virtual factory replication. White paper","author":"Grieves Michael","year":"2014","unstructured":"Michael Grieves. Digital twin: Manufacturing excellence through virtual factory replication. White paper, pages 1--7, 2014."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"e_1_3_2_1_21_1","volume-title":"Reinforcement learning: A survey. Journal of artificial intelligence research, 4:237--285","author":"Kaelbling Leslie Pack","year":"1996","unstructured":"Leslie Pack Kaelbling, Michael L Littman, and Andrew W Moore. Reinforcement learning: A survey. Journal of artificial intelligence research, 4:237--285, 1996."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.08.046"},{"key":"e_1_3_2_1_23_1","first-page":"1008","volume-title":"Advances in neural information processing systems","author":"Konda Vijay R","year":"2000","unstructured":"Vijay R Konda and John N Tsitsiklis. Actor-critic algorithms. In Advances in neural information processing systems, pages 1008--1014, 2000."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2018.08.474"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2019.101837"},{"key":"e_1_3_2_1_26_1","first-page":"17","volume-title":"Multi-Agent Systems","author":"Michel Fabien","year":"2018","unstructured":"Fabien Michel, Jacques Ferber, and Alexis Drogoul. Multi-agent systems and simulation: A survey from the agent commu-nity's perspective. In Multi-Agent Systems, pages 17--66. CRC Press, 2018."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-39931-7_26"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1024176820874"},{"key":"e_1_3_2_1_29_1","volume-title":"World Economic Forum","author":"Schwab Klaus","year":"2017","unstructured":"Klaus Schwab. The fourth industrial revolution. Davos, World Economic Forum, 2017."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014975"},{"key":"e_1_3_2_1_31_1","first-page":"603","volume-title":"ACM Sigplan Notices","author":"Simpkins Christopher","year":"2008","unstructured":"Christopher Simpkins, Sooraj Bhat, Charles Isbell Jr, and Michael Mateas. Towards adaptive programming: integrating reinforcement learning into a programming language. In ACM Sigplan Notices, volume 43, pages 603--614. ACM, 2008."},{"key":"e_1_3_2_1_32_1","volume-title":"Rl-glue: Language-independent software for reinforcement-learning experiments. Journal of Machine Learning Research, 10 (Sep):2133--2136","author":"Tanner Brian","year":"2009","unstructured":"Brian Tanner and Adam White. Rl-glue: Language-independent software for reinforcement-learning experiments. Journal of Machine Learning Research, 10 (Sep):2133--2136, 2009."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2873186"},{"key":"e_1_3_2_1_34_1","first-page":"2011","article-title":"Reengineering aircraft structural life prediction using a digital twin","author":"Tuegel Eric J","year":"2011","unstructured":"Eric J Tuegel, Anthony R Ingraffea, Thomas G Eason, and S Michael Spottswood. Reengineering aircraft structural life prediction using a digital twin. International Journal of Aerospace Engineering, 2011, 2011.","journal-title":"International Journal of Aerospace Engineering"},{"key":"e_1_3_2_1_35_1","volume-title":"Machine learning, 8(3-4): 279--292","author":"Watkins Christopher JCH","year":"1992","unstructured":"Christopher JCH Watkins and Peter Dayan. Q-learning. Machine learning, 8(3-4): 279--292, 1992."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2016.12.168"},{"key":"e_1_3_2_1_37_1","volume-title":"Thirty-Second AAAI Conference on Artificial Intelligence","author":"Zheng Lianmin","year":"2018","unstructured":"Lianmin Zheng, Jiacheng Yang, Han Cai, Ming Zhou, Weinan Zhang, Jun Wang, and Yong Yu. Magent: A many-agent reinforcement learning platform for artificial collective intelligence. In Thirty-Second AAAI Conference on Artificial Intelligence, 2018."}],"event":{"name":"ISEC 2020: 13th Innovations in Software Engineering Conference","sponsor":["iSOFT iSOFT","SIGSOFT ACM Special Interest Group on Software Engineering"],"location":"Jabalpur India","acronym":"ISEC 2020"},"container-title":["Proceedings of the 13th Innovations in Software Engineering Conference (formerly known as India Software Engineering Conference)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3385032.3385041","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3385032.3385041","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:41:13Z","timestamp":1750200073000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3385032.3385041"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,27]]},"references-count":37,"alternative-id":["10.1145\/3385032.3385041","10.1145\/3385032"],"URL":"https:\/\/doi.org\/10.1145\/3385032.3385041","relation":{},"subject":[],"published":{"date-parts":[[2020,2,27]]},"assertion":[{"value":"2020-03-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}