{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T09:27:13Z","timestamp":1769765233456,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T00:00:00Z","timestamp":1699228800000},"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":[[2023,11,6]]},"DOI":"10.1145\/3631085.3631337","type":"proceedings-article","created":{"date-parts":[[2024,1,20]],"date-time":"2024-01-20T00:21:28Z","timestamp":1705710088000},"page":"11-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Scale-Invariant Reinforcement Learning in Real-Time Strategy Games"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5475-5236","authenticated-orcid":false,"given":"Marcelo Luiz Harry Diniz","family":"Lemos","sequence":"first","affiliation":[{"name":", Universidade Federal de Minas Gerais, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7109-0897","authenticated-orcid":false,"given":"Ronaldo E Silva","family":"Vieira","sequence":"additional","affiliation":[{"name":", Universidade Federal de Minas Gerais, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8530-6468","authenticated-orcid":false,"given":"Anderson Rocha","family":"Tavares","sequence":"additional","affiliation":[{"name":", Universidade Federal do Rio Grande do Sul, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3337-8611","authenticated-orcid":false,"given":"Leandro Soriano","family":"Marcolino","sequence":"additional","affiliation":[{"name":", Lancaster University, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8156-9941","authenticated-orcid":false,"given":"Luiz","family":"Chaimowicz","sequence":"additional","affiliation":[{"name":", Universidade Federal de Minas Gerais, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,1,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490409"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/2566972.2566979"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"e_1_3_2_1_4_1","volume-title":"Dota 2 with large scale deep reinforcement learning. arXiv preprint arXiv:1912.06680","author":"Berner Christopher","year":"2019","unstructured":"Christopher Berner, Greg Brockman, Brooke Chan, Vicki Cheung, Przemys\u0142aw D\u0119biak, Christy Dennison, David Farhi, Quirin Fischer, Shariq Hashme, Chris Hesse, 2019. Dota 2 with large scale deep reinforcement learning. arXiv preprint arXiv:1912.06680 (2019)."},{"key":"e_1_3_2_1_5_1","volume-title":"Openai gym. arXiv preprint arXiv:1606.01540","author":"Brockman Greg","year":"2016","unstructured":"Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, John Schulman, Jie Tang, and Wojciech Zaremba. 2016. Openai gym. arXiv preprint arXiv:1606.01540 (2016)."},{"key":"e_1_3_2_1_6_1","volume-title":"How attentive are graph attention networks?arXiv preprint arXiv:2105.14491","author":"Brody Shaked","year":"2021","unstructured":"Shaked Brody, Uri Alon, and Eran Yahav. 2021. How attentive are graph attention networks?arXiv preprint arXiv:2105.14491 (2021)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Machine Learning. PMLR, 2576\u20132585","author":"Han Lei","year":"2019","unstructured":"Lei Han, Peng Sun, Yali Du, Jiechao Xiong, Qing Wang, Xinghai Sun, Han Liu, and Tong Zhang. 2019. Grid-wise control for multi-agent reinforcement learning in video game AI. In International Conference on Machine Learning. PMLR, 2576\u20132585."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.32473\/flairs.v35i.130584"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CoG52621.2021.9619076"},{"key":"e_1_3_2_1_12_1","volume-title":"Efficient entity-based reinforcement learning. arXiv preprint arXiv:2206.02855","author":"Jankovics Vince","year":"2022","unstructured":"Vince Jankovics, Michael\u00a0Garcia Ortiz, and Eduardo Alonso. 2022. Efficient entity-based reinforcement learning. arXiv preprint arXiv:2206.02855 (2022)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v18i1.21954"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_1_15_1","volume-title":"Understanding the difficulty of training transformers. arXiv preprint arXiv:2004.08249","author":"Liu Liyuan","year":"2020","unstructured":"Liyuan Liu, Xiaodong Liu, Jianfeng Gao, Weizhu Chen, and Jiawei Han. 2020. Understanding the difficulty of training transformers. arXiv preprint arXiv:2004.08249 (2020)."},{"key":"e_1_3_2_1_16_1","volume-title":"Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2013. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)."},{"key":"e_1_3_2_1_17_1","volume-title":"International conference on machine learning. PMLR, 1310\u20131318","author":"Pascanu Razvan","year":"2013","unstructured":"Razvan Pascanu, Tomas Mikolov, and Yoshua Bengio. 2013. On the difficulty of training recurrent neural networks. In International conference on machine learning. PMLR, 1310\u20131318."},{"key":"e_1_3_2_1_18_1","volume-title":"The starcraft multi-agent challenge. arXiv preprint arXiv:1902.04043","author":"Samvelyan Mikayel","year":"2019","unstructured":"Mikayel Samvelyan, Tabish Rashid, Christian\u00a0Schroeder De\u00a0Witt, Gregory Farquhar, Nantas Nardelli, Tim\u00a0GJ Rudner, Chia-Man Hung, Philip\u00a0HS Torr, Jakob Foerster, and Shimon Whiteson. 2019. The starcraft multi-agent challenge. arXiv preprint arXiv:1902.04043 (2019)."},{"key":"e_1_3_2_1_19_1","volume-title":"Proximal Policy Optimization Algorithms. CoRR abs\/1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. CoRR abs\/1707.06347 (2017). arXiv:1707.06347http:\/\/arxiv.org\/abs\/1707.06347"},{"key":"e_1_3_2_1_20_1","volume-title":"Julian Schrittwieser, Ioannis Antonoglou","author":"Silver David","year":"2016","unstructured":"David Silver, Aja Huang, Chris\u00a0J Maddison, Arthur Guez, Laurent Sifre, George Van Den\u00a0Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, 2016. Mastering the game of Go with deep neural networks and tree search. Nature 529, 7587 (2016), 484\u2013489."},{"key":"e_1_3_2_1_21_1","volume-title":"Elf: An extensive, lightweight and flexible research platform for real-time strategy games. Advances in Neural Information Processing Systems 30","author":"Tian Yuandong","year":"2017","unstructured":"Yuandong Tian, Qucheng Gong, Wenling Shang, Yuxin Wu, and C\u00a0Lawrence Zitnick. 2017. Elf: An extensive, lightweight and flexible research platform for real-time strategy games. Advances in Neural Information Processing Systems 30 (2017)."},{"key":"e_1_3_2_1_22_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_23_1","volume-title":"Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575, 7782","author":"Vinyals Oriol","year":"2019","unstructured":"Oriol Vinyals, Igor Babuschkin, Wojciech\u00a0M Czarnecki, Micha\u00ebl Mathieu, Andrew Dudzik, Junyoung Chung, David\u00a0H Choi, Richard Powell, Timo Ewalds, Petko Georgiev, 2019. Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575, 7782 (2019), 350\u2013354."},{"key":"e_1_3_2_1_24_1","volume-title":"Starcraft ii: A new challenge for reinforcement learning. arXiv preprint arXiv:1708.04782","author":"Vinyals Oriol","year":"2017","unstructured":"Oriol Vinyals, Timo Ewalds, Sergey Bartunov, Petko Georgiev, Alexander\u00a0Sasha Vezhnevets, Michelle Yeo, Alireza Makhzani, Heinrich K\u00fcttler, John Agapiou, Julian Schrittwieser, 2017. Starcraft ii: A new challenge for reinforcement learning. arXiv preprint arXiv:1708.04782 (2017)."},{"key":"e_1_3_2_1_25_1","volume-title":"International Conference on Machine Learning. PMLR, 10905\u201310915","author":"Wang Xiangjun","year":"2021","unstructured":"Xiangjun Wang, Junxiao Song, Penghui Qi, Peng Peng, Zhenkun Tang, Wei Zhang, Weimin Li, Xiongjun Pi, Jujie He, Chao Gao, 2021. SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II. In International Conference on Machine Learning. PMLR, 10905\u201310915."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMC52423.2021.9658625"}],"event":{"name":"SBGames 2023: 22nd Brazilian Symposium on Games and Digital Entertainment","location":"Rio Grande (RS) Brazil","acronym":"SBGames 2023"},"container-title":["Proceedings of the 22nd Brazilian Symposium on Games and Digital Entertainment"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3631085.3631337","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3631085.3631337","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T02:22:35Z","timestamp":1755915755000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3631085.3631337"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,6]]},"references-count":26,"alternative-id":["10.1145\/3631085.3631337","10.1145\/3631085"],"URL":"https:\/\/doi.org\/10.1145\/3631085.3631337","relation":{},"subject":[],"published":{"date-parts":[[2023,11,6]]},"assertion":[{"value":"2024-01-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}