{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T06:38:38Z","timestamp":1769755118743,"version":"3.49.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","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\/501100011347","name":"State Key Laboratory of Software Development Environment","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611035","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"10814-10820","source":"Crossref","is-referenced-by-count":6,"title":["AdaptAUG: Adaptive Data Augmentation Framework for Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Xin","family":"Yu","sequence":"first","affiliation":[{"name":"Beihang University,School of Computer Science and Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongkai","family":"Tian","sequence":"additional","affiliation":[{"name":"Beihang University,School of Computer Science and Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Wang","sequence":"additional","affiliation":[{"name":"Beihang University,Institute of Artificial Intelligence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pu","family":"Feng","sequence":"additional","affiliation":[{"name":"Beihang University,School of Computer Science and Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjun","family":"Wu","sequence":"additional","affiliation":[{"name":"Beihang University,Institute of Artificial Intelligence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongye","family":"Shi","sequence":"additional","affiliation":[{"name":"Beihang University,Institute of Artificial Intelligence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2297","article-title":"Coordinated multiagent reinforcement learning for teams of mobile sensing robots","volume-title":"Proceedings of the 18th international conference on autonomous agents and multiagent systems","author":"Yu"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09997-9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11396"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM52615.2021.9669656"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230609"},{"key":"ref6","first-page":"5402","article-title":"Automatic data augmentation for generalization in reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Raileanu"},{"key":"ref7","first-page":"1","article-title":"Improving sample efficiency in multi-agent actor-critic methods","author":"Ye","year":"2021","journal-title":"Applied Intelligence"},{"key":"ref8","article-title":"Reinforcement learning with augmented data","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Laskin"},{"key":"ref9","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Cobbe"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2013.6707036"},{"key":"ref11","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"International Conference on Learning Representations","author":"Yarats"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3013937"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2898330"},{"key":"ref14","article-title":"Data-efficient reinforcement learning with self-predictive representations","author":"Schwarzer","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref17","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"International conference on learning representations","author":"Yarats"},{"key":"ref18","article-title":"Sample-efficient reinforcement learning via counterfactual-based data augmentation","author":"Lu","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3233\/faia230609"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3307134"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref22","article-title":"Improving the pareto ucb1 algorithm on the multi-objective multi-armed bandit","volume-title":"Workshop of the 27th Neural Information Processing (NIPS) on Bayesian Optimization","author":"Durand"},{"key":"ref23","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Rashid"},{"key":"ref24","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"Lowe","year":"2017"},{"key":"ref25","article-title":"The surprising effectiveness of ppo in cooperative, multi-agent games","author":"Yu","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11492"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-36625-3_7"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068952"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/icde60146.2024.00196"},{"key":"ref30","article-title":"Byzantine robust cooperative multi-agent reinforcement learning as a bayesian game","author":"Li","year":"2023"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611035.pdf?arnumber=10611035","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:23:33Z","timestamp":1723267413000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611035\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611035","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}