{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:33:19Z","timestamp":1730266399572,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650452","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Self-Attention Guided Advice Distillation in Multi-Agent Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Yang","family":"Li","sequence":"first","affiliation":[{"name":"Dalian University of Technology,College of Computer Science and Technology,Dalian,China,116024"}]},{"given":"Sihan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,College of Computer Science and Technology,Dalian,China,116024"}]},{"given":"Yaqing","family":"Hou","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,College of Computer Science and Technology,Dalian,China,116024"}]},{"given":"Liran","family":"Zhou","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,College of Computer Science and Technology,Dalian,China,116024"}]},{"given":"Hongwei","family":"Ge","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,College of Computer Science and Technology,Dalian,China,116024"}]},{"given":"Liang","family":"Feng","sequence":"additional","affiliation":[{"name":"Chongqing University,College of Computer Science,Chongqing,China,400044"}]},{"given":"Siyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Chongqing University,College of Computer Science,Chongqing,China,400044"}]}],"member":"263","reference":[{"volume-title":"Reinforcement learning: An introduction.","year":"2018","author":"Sutton","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292075"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09430-0"},{"key":"ref4","first-page":"1053","article-title":"Teaching on a budget: Agents advising agents in reinforcement learning","volume-title":"Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems","author":"Torrey"},{"key":"ref5","first-page":"1100","article-title":"Simultaneously learning and advising in multiagent reinforcement learning","volume-title":"Proceedings of the 16th conference on autonomous agents and multiagent systems","author":"Da Silva"},{"key":"ref6","first-page":"2324","article-title":"A q-values sharing framework for multiple independent q-learners","author":"Zhu","year":"2019","journal-title":"AAMAS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref8","article-title":"Maven: Multi-agent variational exploration","volume":"32","author":"Mahajan","year":"2019","journal-title":"Advances in neural information processing systems"},{"issue":"1","key":"ref9","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8847988"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6036"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016128"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2200\/s01091ed1v01y202104aim049"},{"key":"ref16","first-page":"1674","article-title":"Learning by reusing previous advice in teacher-student paradigm","volume-title":"Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems","author":"Zhu"},{"key":"ref17","first-page":"1","article-title":"Heterogeneous knowledge transfers via hierarchical teaching in cooperative multiagent reinforcement learning","volume-title":"Proc of the 19th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2020)","author":"Kim"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"journal-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref19"},{"key":"ref20","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref21","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron"},{"article-title":"Learning from delayed rewards","year":"1989","author":"Watkins","key":"ref22"},{"key":"ref23","first-page":"1388","article-title":"A deep policy inference q-network for multi-agent systems","volume-title":"Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems","author":"Hong"},{"article-title":"Interactive teaching strategies for agent training","volume-title":"Proceedings of IJCAI 2016","author":"Amir","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3034424"},{"journal-title":"Exploration by random network distillation","year":"2018","author":"Burda","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3113644"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_36"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3147011"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650452.pdf?arnumber=10650452","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:20:56Z","timestamp":1725945656000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650452\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650452","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}