{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:40:51Z","timestamp":1730266851077,"version":"3.28.0"},"reference-count":33,"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\/100018913","name":"Tsinghua Shenzhen International Graduate School","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018913","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\/ijcnn60899.2024.10651270","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Task-agnostic Decision Transformer for Multi-type Agent Control with Federated Split Training"],"prefix":"10.1109","author":[{"given":"Zhiyuan","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Bokui","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Tsinghua Shenzhen International Graduate School,Shenzhen,China"}]},{"given":"Xiaoyang","family":"Qu","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}]},{"given":"Zhenhou","family":"Hong","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}]},{"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}]},{"given":"Jianzong","family":"Wang","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-023-2689-5"},{"key":"ref3","first-page":"368","article-title":"How you act tells a lot: Privacy-leaking attack on deep reinforcement learning","volume-title":"International Conference on Autonomous Agents and Multiagent Systems","author":"Pan"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888913000180"},{"key":"ref5","first-page":"810","article-title":"Fedformer: Contextual federation with attention in reinforcement learning","volume-title":"International Conference on Autonomous Agents and Multiagent Systems","author":"Hebert"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10348-5"},{"key":"ref7","first-page":"15 084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"27 921","article-title":"Multi-game decision transformers","volume":"35","author":"Lee","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","first-page":"27 042","article-title":"Online decision transformer","volume-title":"International Conference on Machine Learning","author":"Zheng"},{"article-title":"Hyper-decision transformer for efficient online policy adaptation","volume-title":"International Conference on Learning Representations","author":"Xu","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447775"},{"key":"ref12","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017","journal-title":"Artificial intelligence and statistics"},{"key":"ref13","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proceedings of Machine learning and systems","volume":"2","author":"Li"},{"key":"ref14","first-page":"374","article-title":"Towards federated learning at scale: System design","volume-title":"Proceedings of machine learning and systems","volume":"1","author":"Bonawitz"},{"key":"ref15","first-page":"3557","article-title":"Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach","volume":"33","author":"Fallah","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","article-title":"Federated multi-task learning","volume":"30","author":"Smith","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/443"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC-SmartCity-DSS50907.2020.00129"},{"article-title":"Fit: Parameter efficient few-shot transfer learning for person-alized and federated image classification","volume-title":"International Conference on Learning Representations","author":"Shysheya","key":"ref19"},{"article-title":"Split learning for health: Distributed deep learning without sharing raw patient data","year":"2018","author":"Vepakomma","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3242704"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20825"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-15184-5"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00074"},{"issue":"8","key":"ref25","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref26","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00982"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3218783"},{"key":"ref29","first-page":"24 617","article-title":"Federated split task-agnostic vision transformer for covid-19 cxr diagnosis","volume":"34","author":"Park","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","volume":"32","author":"Kumar","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Behavior regularized offline reinforcement learning","year":"2019","author":"Wu","key":"ref32"},{"article-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","year":"2019","author":"Peng","key":"ref33"}],"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\/10651270.pdf?arnumber=10651270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T06:38:50Z","timestamp":1725950330000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10651270\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10651270","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}