{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T01:04:31Z","timestamp":1789607071613,"version":"build-2803163510"},"reference-count":67,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.neucom.2026.134529","type":"journal-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:25:12Z","timestamp":1784179512000},"page":"134529","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Top-k uniform projection for training-free policy fusion in sequential decision making"],"prefix":"10.1016","volume":"701","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4791-1624","authenticated-orcid":false,"given":"Bocheng","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0221-7171","authenticated-orcid":false,"given":"Wucheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4006-1700","authenticated-orcid":false,"given":"Zhihong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5015-238X","authenticated-orcid":false,"given":"Jingyi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8906-7325","authenticated-orcid":false,"given":"Wenxing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2872-388X","authenticated-orcid":false,"given":"Qiguang","family":"Miao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134529_bib0005","doi-asserted-by":"crossref","first-page":"35921","DOI":"10.52202\/068431-2603","article-title":"DNA: proximal policy optimization with a dual network architecture","volume":"35","author":"Aitchison","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134529_bib0010","author":"An"},{"key":"10.1016\/j.neucom.2026.134529_bib0015","author":"Anderson"},{"key":"10.1016\/j.neucom.2026.134529_bib0020","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3674","article-title":"Vision-and-language navigation: interpreting visually-grounded navigation instructions in real environments","author":"Anderson","year":"2018"},{"key":"10.1016\/j.neucom.2026.134529_bib0025","series-title":"International Conference on Machine Learning","first-page":"243","article-title":"An alternative softmax operator for reinforcement learning","author":"Asadi","year":"2017"},{"key":"10.1016\/j.neucom.2026.134529_bib0030","series-title":"International Conference on Machine Learning","first-page":"507","article-title":"Agent57: outperforming the atari human benchmark","author":"Badia","year":"2020"},{"key":"10.1016\/j.neucom.2026.134529_bib0035","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1023\/A:1018054314350","article-title":"Bagging predictors","volume":"24","author":"Breiman","year":"1996","journal-title":"Mach. Learn."},{"key":"10.1016\/j.neucom.2026.134529_bib0040","author":"Burda"},{"key":"10.1016\/j.neucom.2026.134529_bib0045","article-title":"Boltzmann exploration done right","volume":"30","author":"Cesa-Bianchi","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134529_bib0050","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume":"34","author":"Chen","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134529_bib0055","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16537","article-title":"Think global, act local: dual-scale graph transformer for vision-and-language navigation","author":"Chen","year":"2022"},{"key":"10.1016\/j.neucom.2026.134529_bib0060","series-title":"Proceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval","first-page":"758","article-title":"Reciprocal rank fusion outperforms condorcet and individual rank learning methods","author":"Cormack","year":"2009"},{"key":"10.1016\/j.neucom.2026.134529_bib0065","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"12043","article-title":"Grounded entity-landmark adaptive pre-training for vision-and-language navigation","author":"Cui","year":"2023"},{"key":"10.1016\/j.neucom.2026.134529_bib0070","series-title":"International Workshop on Multiple Classifier Systems","first-page":"1","article-title":"Ensemble methods in machine learning","author":"Dietterich","year":"2000"},{"key":"10.1016\/j.neucom.2026.134529_bib0075","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1038\/s41586-020-03157-9","article-title":"First return, then explore","volume":"590","author":"Ecoffet","year":"2021","journal-title":"Nature"},{"key":"10.1016\/j.neucom.2026.134529_bib0080","doi-asserted-by":"crossref","first-page":"29986","DOI":"10.52202\/079017-0944","article-title":"On giant\u2019s shoulders: effortless weak to strong by dynamic logits fusion","volume":"37","author":"Fan","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134529_bib0085","author":"Fan"},{"key":"10.1016\/j.neucom.2026.134529_bib0090","article-title":"Speaker-follower models for vision-and-language navigation","volume":"31","author":"Fried","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134529_bib0095","series-title":"International Conference on Algorithmic Learning Theory","first-page":"174","article-title":"On upper-confidence bound policies for switching bandit problems","author":"Garivier","year":"2011"},{"key":"10.1016\/j.neucom.2026.134529_bib0100","series-title":"Conference on Learning Theory","first-page":"861","article-title":"Thompson sampling for learning parameterized Markov decision processes","author":"Gopalan","year":"2015"},{"key":"10.1016\/j.neucom.2026.134529_bib0105","author":"Gopinathan"},{"key":"10.1016\/j.neucom.2026.134529_bib0110","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"1634","article-title":"Airbert: in-domain pretraining for vision-and-language navigation","author":"Guhur","year":"2021"},{"key":"10.1016\/j.neucom.2026.134529_bib0115","series-title":"International Conference on Machine Learning","first-page":"1321","article-title":"On calibration of modern neural networks","author":"Guo","year":"2017"},{"key":"10.1016\/j.neucom.2026.134529_bib0120","author":"Hafner"},{"key":"10.1016\/j.neucom.2026.134529_bib0125","series-title":"The Fourteenth International Conference on Learning Representations","article-title":"EMFuse: energy-based model fusion for decision making","author":"He","year":"2026"},{"key":"10.1016\/j.neucom.2026.134529_bib0130","author":"Hinton"},{"key":"10.1016\/j.neucom.2026.134529_bib0135","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1643","article-title":"Vln BERT: a recurrent vision-and-language BERT for navigation","author":"Hong","year":"2021"},{"key":"10.1016\/j.neucom.2026.134529_bib0140","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"23212","article-title":"GeoVLN: learning geometry-enhanced visual representation with slot attention for vision-and-language navigation","author":"Huo","year":"2023"},{"key":"10.1016\/j.neucom.2026.134529_bib0145","author":"Ilharco"},{"key":"10.1016\/j.neucom.2026.134529_bib0150","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","article-title":"Adaptive mixtures of local experts","volume":"3","author":"Jacobs","year":"1991","journal-title":"Neural Comput."},{"key":"10.1016\/j.neucom.2026.134529_bib0155","author":"Jain"},{"key":"10.1016\/j.neucom.2026.134529_bib0160","author":"Kong"},{"key":"10.1016\/j.neucom.2026.134529_bib0165","article-title":"Neural network ensembles, cross validation, and active learning","volume":"7","author":"Krogh","year":"1994","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134529_bib0170","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10803","article-title":"Improving vision-and-language navigation by generating future-view image semantics","author":"Li","year":"2023"},{"key":"10.1016\/j.neucom.2026.134529_bib0175","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15407","article-title":"Envedit: environment editing for vision-and-language navigation","author":"Li","year":"2022"},{"key":"10.1016\/j.neucom.2026.134529_bib0180","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2583","article-title":"Kerm: knowledge enhanced reasoning for vision-and-language navigation","author":"Li","year":"2023"},{"key":"10.1016\/j.neucom.2026.134529_bib0185","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"1592","article-title":"Contrastive instruction-trajectory learning for vision-language navigation","author":"Liang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134529_bib0190","series-title":"International Conference on Learning Representations","first-page":"57333","article-title":"Maximum entropy heterogeneous-agent reinforcement learning","author":"Liu","year":"2024"},{"key":"10.1016\/j.neucom.2026.134529_bib0195","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134529_bib0200","author":"Mnih"},{"key":"10.1016\/j.neucom.2026.134529_bib0205","article-title":"Deep exploration via bootstrapped DQN","volume":"29","author":"Osband","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134529_bib0210","author":"Pan"},{"key":"10.1016\/j.neucom.2026.134529_bib0215","author":"Pearce"},{"key":"10.1016\/j.neucom.2026.134529_bib0220","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128033","article-title":"Self-supervised network distillation: an effective approach to exploration in sparse reward environments","author":"Pech\u00e1\u010d","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134529_bib0225","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15418","article-title":"Hop: history-and-order aware pre-training for vision-and-language navigation","author":"Qiao","year":"2022"},{"key":"10.1016\/j.neucom.2026.134529_bib0230","series-title":"International Conference on Machine Learning","first-page":"18168","article-title":"Contrastive ucb: provably efficient contrastive self-supervised learning in online reinforcement learning","author":"Qiu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134529_bib0235","series-title":"Proceedings of the 35th International Conference on Machine Learning","first-page":"4295","article-title":"QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"vol. 80","author":"Rashid","year":"2018"},{"key":"10.1016\/j.neucom.2026.134529_bib0240","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000070","article-title":"A tutorial on thompson sampling","volume":"11","author":"Russo","year":"2018","journal-title":"Found. Trends\u00ae Mach. Learn."},{"key":"10.1016\/j.neucom.2026.134529_bib0245","author":"Rusu"},{"key":"10.1016\/j.neucom.2026.134529_bib0250","author":"Samvelyan"},{"key":"10.1016\/j.neucom.2026.134529_bib0255","doi-asserted-by":"crossref","first-page":"604","DOI":"10.1038\/s41586-020-03051-4","article-title":"Mastering atari, go, chess and shogi by planning with a learned model","volume":"588","author":"Schrittwieser","year":"2020","journal-title":"Nature"},{"key":"10.1016\/j.neucom.2026.134529_bib0260","first-page":"27580","article-title":"Online and offline reinforcement learning by planning with a learned model","volume":"34","author":"Schrittwieser","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134529_bib0265","author":"Shazeer"},{"key":"10.1016\/j.neucom.2026.134529_bib0270","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1023\/A:1007678930559","article-title":"Convergence results for single-step on-policy reinforcement-learning algorithms","volume":"38","author":"Singh","year":"2000","journal-title":"Mach. Learn."},{"key":"10.1016\/j.neucom.2026.134529_bib0275","series-title":"Proceedings of International Conference on Neural Networks (ICNN\u201996)","first-page":"90","article-title":"Generalization error of ensemble estimators","author":"Ueda","year":"1996"},{"key":"10.1016\/j.neucom.2026.134529_bib0280","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.neucom.2016.09.141","article-title":"Softmax exploration strategies for multiobjective reinforcement learning","volume":"263","author":"Vamplew","year":"2017","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134529_bib0285","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"12009","article-title":"Scaling data generation in vision-and-language navigation","author":"Wang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134529_bib0290","doi-asserted-by":"crossref","first-page":"930","DOI":"10.1109\/TSMCB.2008.920231","article-title":"Ensemble algorithms in reinforcement learning","volume":"38","author":"Wiering","year":"2008","journal-title":"IEEE Trans. Syst. Man Cybern. B (Cybern.)"},{"key":"10.1016\/j.neucom.2026.134529_bib0295","first-page":"1","article-title":"Dynamic weights and prior reward in policy fusion for compound agent learning","volume":"14","author":"Xu","year":"2023","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"10.1016\/j.neucom.2026.134529_bib0300","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.124929","article-title":"A hyper-heuristic algorithm via proximal policy optimization for multi-objective truss problems","volume":"256","author":"Yin","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.neucom.2026.134529_bib0305","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.127491","article-title":"Adaptive operator selection with dueling deep Q-Network for evolutionary multi-objective optimization","volume":"581","author":"Yin","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134529_bib0310","doi-asserted-by":"crossref","DOI":"10.1016\/j.swevo.2025.102251","article-title":"Multi-objective collaborative path planning for heterogeneous autonomous underwater vehicles in cluttered environments","volume":"100","author":"Yin","year":"2026","journal-title":"Swarm Evol. Comput."},{"key":"10.1016\/j.neucom.2026.134529_bib0315","doi-asserted-by":"crossref","first-page":"24611","DOI":"10.52202\/068431-1787","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134529_bib0320","author":"Zhang"},{"key":"10.1016\/j.neucom.2026.134529_bib0325","author":"Zhang"},{"key":"10.1016\/j.neucom.2026.134529_bib0330","article-title":"A new ensemble learning method for multiple fusion weighted evidential reasoning rule","volume":"2023","author":"Zhang","year":"2023","journal-title":"J. Electr. Comput. Eng."},{"key":"10.1016\/j.neucom.2026.134529_bib0335","first-page":"1","article-title":"Heterogeneous-agent reinforcement learning","volume":"25","author":"Zhong","year":"2024","journal-title":"J. Mach. Learn. Res."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226019272?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226019272?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T00:25:50Z","timestamp":1789604750000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226019272"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":67,"alternative-id":["S0925231226019272"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134529","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Top- uniform projection for training-free policy fusion in sequential decision making","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134529","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"134529"}}