{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T19:39:58Z","timestamp":1780515598867,"version":"3.54.1"},"reference-count":37,"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\/ijcnn54540.2023.10191536","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T13:30:03Z","timestamp":1690983003000},"page":"1-8","source":"Crossref","is-referenced-by-count":3,"title":["T3S: Improving Multi-Task Reinforcement Learning with Task-Specific Feature Selector and Scheduler"],"prefix":"10.1109","author":[{"given":"Yuanqiang","family":"Yu","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianpei","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Alberta and Alberta Machine Intelligence Institute,Department of Computing Science,Edmonton,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongliang","family":"Lv","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Zheng","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianye","family":"Hao","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume":"100","author":"yu","year":"2020","journal-title":"Proceedings of the Conference on Robot Learning ser Proceedings of Machine Learning Research"},{"key":"ref35","article-title":"Actor-mimic: Deep multitask and transfer reinforcement learning","author":"parisotto","year":"2016","journal-title":"4th International Conference on Learning Representations ICLR 2016 San Juan Puerto Rico May 2–4 2016 Conference Track Proceedings"},{"key":"ref12","author":"crawshaw","year":"2020","journal-title":"Multi-Task Learning with Deep Neural Networks A Survey"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412236"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"ref37","article-title":"Just pick a sign: Optimizing deep multitask models with gradient sign dropout","author":"chen","year":"2020","journal-title":"Advances in Neural Information Processing Systems 33 Annual Conference on Neural Information Processing Systems 2020 NeurIPS 2020 December 6–12 2020 virtual"},{"key":"ref14","first-page":"3994","article-title":"Cross-stitch net-works for multi-task learning","author":"misra","year":"2016","journal-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition CVPR 2016"},{"key":"ref36","article-title":"Policy distillation","author":"rusu","year":"2016","journal-title":"4th International Conference on Learning Representations ICLR 2016 San Juan Puerto Rico May 2–4 2016 Conference Track Proceedings"},{"key":"ref31","author":"rosenbaum","year":"2017","journal-title":"Routing networks Adaptive selection of nonlinear functions for multi-task learning"},{"key":"ref30","author":"fernando","year":"2017","journal-title":"Evolution Channels Gradient Descent in Super Neural Networks"},{"key":"ref11","first-page":"264","article-title":"Smarts: An open-source scalable multi-agent rl training school for autonomous driving","volume":"155","author":"zhou","year":"0","journal-title":"Proceedings of the 2020 Conference on Robot Learning ser Proceedings of Machine Learning Research"},{"key":"ref33","article-title":"Adashare: Learning what to share for efficient deep multi-task learning","author":"sun","year":"2020","journal-title":"Advances in Neural Information Processing Systems 33 Annual Conference on Neural Information Processing Systems 2020 NeurIPS 2020 December 6–12 2020 virtual"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304542"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00810"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref17","article-title":"Multi-task reinforcement learning with soft modularization","author":"yang","year":"2020","journal-title":"Advances in Neural Information Processing Systems 33 Annual Conference on Neural Information Processing Systems 2020 NeurIPS 2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref19","first-page":"18878","article-title":"Conflict-averse gradi-ent descent for multi-task learning","volume":"34","author":"liu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Gradient surgery for multi-task learning","author":"yu","year":"2020","journal-title":"Advances in Neural Information Processing Systems 33 Annual Conference on Neural Information Processing Systems 2020 NeurIPS 2020"},{"key":"ref24","first-page":"9301","article-title":"Recomposing the reinforcement learning building blocks with hypernetworks","volume":"139","author":"sarafian","year":"2021","journal-title":"Proceedings of the 38th International Conference on Machine Learning ICML 2021 18–24 July 2021 Virtual Event ser Proceedings of Machine Learning Research"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.1.131"},{"key":"ref26","article-title":"Hypernetworks","author":"ha","year":"2017","journal-title":"5th International Conference on Learning Representations ICLR 2017 Toulon France April 24–26 2017 Conference Track Proceedings"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560793"},{"key":"ref20","article-title":"Learning to multi-task by active sampling","author":"sharma","year":"2018","journal-title":"6th International conference on Learning Representations ICLR 2018 Vancouver BC Canada April 30 - May 3 2018 Conference Track Proceedings"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog0901_6"},{"key":"ref21","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018","journal-title":"ArXiv preprint vol abs\/1812 05905"},{"key":"ref28","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref29","article-title":"Visualizing data using t-sne","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16914"},{"key":"ref9","article-title":"Deep reinforcement learning for autonomous driving: A survey","author":"kiran","year":"2021","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref4","first-page":"17037","article-title":"An efficient transfer learning framework for multi agent reinforcement learning","volume":"34","author":"yang","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref3","volume":"abs 1912 6680","author":"berner","year":"2019","journal-title":"Dota 2 with large scale deep reinforcement learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00077"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","location":"Gold Coast, Australia","start":{"date-parts":[[2023,6,18]]},"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\/10191536.pdf?arnumber=10191536","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T13:46:29Z","timestamp":1692625589000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191536\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191536","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}