{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T13:00:35Z","timestamp":1748782835661,"version":"3.28.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191816","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"1-9","source":"Crossref","is-referenced-by-count":1,"title":["Cooperation Skill Motivated Reinforcement Learning for Traffic Signal Control"],"prefix":"10.1109","author":[{"given":"Jie","family":"Xin","sequence":"first","affiliation":[{"name":"Hikvision Research Institude,Hangzhou,China,310051"}]},{"given":"Jing","family":"Zeng","sequence":"additional","affiliation":[{"name":"Hikvision Research Institude,Hangzhou,China,310051"}]},{"given":"Ya","family":"Cong","sequence":"additional","affiliation":[{"name":"Hikvision Research Institude,Hangzhou,China,310051"}]},{"given":"Weihao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Hikvision Research Institude,Hangzhou,China,310051"}]},{"given":"Shiliang","family":"Pu","sequence":"additional","affiliation":[{"name":"Hikvision Research Institude,Hangzhou,China,310051"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/9781420085891-p1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1057\/jors.1963.61"},{"key":"ref3","article-title":"Maxband: A program for setting signals on arteries and triangular networks","author":"Little","year":"1981","journal-title":"Research Papers in Economics"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220096"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357902"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16147"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357900"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5467"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/345"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569301"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2022.3232711"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/535"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330949"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"ref16","first-page":"26645","article-title":"Expression might be enough: Representing pressure and demand for reinforcement learning based traffic signal control","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Zhang"},{"issue":"9","key":"ref17","first-page":"816","article-title":"Feudal multi-agent deep reinforcement learning for traffic signal control","volume-title":"Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems","author":"Ma","year":"2020"},{"key":"ref18","article-title":"Diversity is all you need: Learning skills without a reward function","volume-title":"International Conference on Learning Representations","author":"Eysenbach","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-53734-9_4"},{"key":"ref20","article-title":"Variational intrinsic control","author":"Gregor","year":"2016","journal-title":"arXiv preprint"},{"key":"ref21","first-page":"2125","article-title":"Variational information maximisation for intrinsically motivated reinforcement learning","volume-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems","author":"Mohamed"},{"key":"ref22","article-title":"Dynamics-aware unsupervised discovery of skills","volume-title":"International Conference on Learning Representations","author":"Sharma","year":"2020"},{"key":"ref23","first-page":"1317","article-title":"Explore, discover and learn: Unsupervised discovery of state-covering skills","volume-title":"Proceedings of the 37th International Conference on Machine Learning","volume":"119","author":"Campos"},{"key":"ref24","first-page":"1566","article-title":"Hierarchical cooperative multiagent reinforcement learning with skill discovery","volume-title":"Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems","author":"Yang","year":"2020"},{"key":"ref25","article-title":"Learning to coordinate manipulation skills via skill behavior diversification","volume-title":"International Conference on Learning Representations","author":"Lee","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16832"},{"key":"ref27","article-title":"Learning more skills through optimistic exploration","volume-title":"International Conference on Learning Representations","author":"Srouse","year":"2022"},{"key":"ref28","first-page":"201","article-title":"The im algorithm: A variational approach to information maximization","volume-title":"Proceedings of the 16th International Conference on Neural Information Processing Systems","author":"Barber"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v031.i07"},{"key":"ref30","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"The surprising effectiveness of mappo in cooperative, multi-agent games","author":"Yu","year":"2021","journal-title":"arXiv preprint"},{"issue":"3&4","key":"ref33","first-page":"128","article-title":"Recent development and applications of sumo - simulation of urban mobility","volume":"5","author":"Krajzewicz","year":"2012","journal-title":"International Journal On Advances in Systems and Measurements"},{"key":"ref34","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proceedings of the 33nd International Conference on Machine Learning","volume":"48","author":"Mnih"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2023,6,18]]},"location":"Gold Coast, Australia","end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191816.pdf?arnumber=10191816","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T15:29:22Z","timestamp":1709306962000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191816\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191816","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}