{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:10:41Z","timestamp":1740100241942,"version":"3.37.3"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100015539","name":"Australian Government","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015539","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP190102828"],"award-info":[{"award-number":["DP190102828"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9533975","type":"proceedings-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T21:27:41Z","timestamp":1632173261000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Domain-Aware Multiagent Reinforcement Learning in Navigation"],"prefix":"10.1109","author":[{"given":"Ifrah","family":"Saeed","sequence":"first","affiliation":[{"name":"The University of Melbourne,Department of Electrical and Electronic Engineering,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew C.","family":"Cullen","sequence":"additional","affiliation":[{"name":"The University of Melbourne,School of Computing and Information Systems,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarah","family":"Erfani","sequence":"additional","affiliation":[{"name":"The University of Melbourne,School of Computing and Information Systems,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tansu","family":"Alpcan","sequence":"additional","affiliation":[{"name":"The University of Melbourne,Department of Electrical and Electronic Engineering,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","first-page":"1495","article-title":"Emergence of grounded compositional language in multi-agent populations","author":"mordatch","year":"2018","journal-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-02094-0_7"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref30"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2015.12.017"},{"key":"ref11","article-title":"How to use deep learning with your internet of things (IoT) digital twin","author":"klenz","year":"0","journal-title":"Proceedings of the SAS Global Forum 2019 Conference"},{"key":"ref12","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume":"97","author":"iqbal","year":"0","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref13","article-title":"Benchmarking model-based reinforcement learning","author":"langlois","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref14","article-title":"Model-based multi-agent reinforcement learning with cooperative prioritized sweeping","author":"bargiacchi","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref15","first-page":"1","article-title":"Model predictive control guided reinforcement learning control scheme","author":"xie","year":"0","journal-title":"Proceedings of the International Joint Conference on Neural Networks"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11396"},{"key":"ref17","first-page":"177","article-title":"Input addition and deletion in reinforcement: Towards learning with structural changes","author":"bonnici","year":"0","journal-title":"Proceedings of the International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30484-3_48"},{"key":"ref19","first-page":"9876","article-title":"ROMA: Multi-agent reinforcement learning with emergent roles","author":"wang","year":"0","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref28","article-title":"Multiagent soft q-learning","author":"wei","year":"2018","journal-title":"Proceedings of AAAI Spring Symposium Series"},{"key":"ref4","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"0","journal-title":"Proceedings of Advances in Neural Information Processing Systems"},{"key":"ref27","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"0","journal-title":"Proceedings of Advances in Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"key":"ref6","article-title":"Model-based reinforcement learning: A survey","author":"moerland","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref29","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume":"80","author":"haarnoja","year":"0","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref5","first-page":"2974","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref7","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref2","article-title":"The computational limits of deep learning","author":"thompson","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref9","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"ng","year":"0","journal-title":"Proceedings of International Conference on Machine Learning"},{"key":"ref1","article-title":"Multi-agent reinforcement learning: A selective overview of theories and algorithms","author":"zhang","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref20","first-page":"225","article-title":"Theoretical considerations of potential-based reward shaping for multi-agent systems","author":"devlin","year":"0","journal-title":"Proceedings of the International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref22","first-page":"4644","article-title":"On learning intrinsic rewards for policy gradient methods","author":"zheng","year":"0","journal-title":"Proceedings of Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278759"},{"key":"ref24","first-page":"1332","article-title":"Can agents learn by analogy? an inferable model for pac reinforcement learning","author":"sun","year":"0","journal-title":"Proceedings of the International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/324"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref25","first-page":"11 436","article-title":"What can learned intrinsic rewards capture?","author":"zheng","year":"0","journal-title":"Proceedings of International Conference on Machine Learning"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2021,7,18]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09533975.pdf?arnumber=9533975","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:32:13Z","timestamp":1659483133000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9533975\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9533975","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}