{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T09:53:03Z","timestamp":1720173183307},"reference-count":67,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2022,5,20]],"date-time":"2022-05-20T00:00:00Z","timestamp":1653004800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000268","name":"BBSRC","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000268","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1016\/j.neunet.2022.03.015","type":"journal-article","created":{"date-parts":[[2022,3,17]],"date-time":"2022-03-17T13:37:17Z","timestamp":1647524237000},"page":"408-421","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["Selective particle attention: Rapidly and flexibly selecting features for deep reinforcement learning"],"prefix":"10.1016","volume":"150","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-5023-7933","authenticated-orcid":false,"given":"Sam","family":"Blakeman","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-9828-9548","authenticated-orcid":false,"given":"Denis","family":"Mareschal","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2022.03.015_b1","doi-asserted-by":"crossref","first-page":"798","DOI":"10.2307\/1130217","article-title":"Attentional inertia reduces distractibility during young children\u2019s TV viewing","author":"Anderson","year":"1987","journal-title":"Child Development"},{"key":"10.1016\/j.neunet.2022.03.015_b2","unstructured":"Bengio, Y. (2012). Deep learning of representations for unsupervised and transfer learning. In Proceedings of ICML workshop on unsupervised and transfer learning (pp. 17\u201336)."},{"key":"10.1016\/j.neunet.2022.03.015_b3","series-title":"Particle filter-based policy gradient in POMDPs","author":"Besse","year":"2009"},{"issue":"4","key":"10.1016\/j.neunet.2022.03.015_b4","doi-asserted-by":"crossref","first-page":"832","DOI":"10.1016\/j.neuron.2015.10.001","article-title":"A source for feature-based attention in the prefrontal cortex","volume":"88","author":"Bichot","year":"2015","journal-title":"Neuron"},{"key":"10.1016\/j.neunet.2022.03.015_b5","article-title":"Generalized attention-weighted reinforcement learning","author":"Bramlage","year":"2021","journal-title":"Neural Networks"},{"issue":"6","key":"10.1016\/j.neunet.2022.03.015_b6","doi-asserted-by":"crossref","first-page":"777","DOI":"10.1177\/009365093020006002","article-title":"Attentional inertia and recognition memory in adult television viewing","volume":"20","author":"Burns","year":"1993","journal-title":"Communication Research"},{"issue":"1","key":"10.1016\/j.neunet.2022.03.015_b7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-017-17687-2","article-title":"Exploring feature dimensions to learn a new policy in an uninformed reinforcement learning task","volume":"7","author":"Choung","year":"2017","journal-title":"Scientific Reports"},{"issue":"6","key":"10.1016\/j.neunet.2022.03.015_b8","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","article-title":"The mnist database of handwritten digit images for machine learning research [best of the web]","volume":"29","author":"Deng","year":"2012","journal-title":"IEEE Signal Processing Magazine"},{"key":"10.1016\/j.neunet.2022.03.015_b9","series-title":"2009 IEEE conference on computer vision and pattern recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"issue":"1","key":"10.1016\/j.neunet.2022.03.015_b10","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1146\/annurev.ne.18.030195.001205","article-title":"Neural mechanisms of selective visual attention","volume":"18","author":"Desimone","year":"1995","journal-title":"Annual Review of Neuroscience"},{"issue":"6191","key":"10.1016\/j.neunet.2022.03.015_b11","doi-asserted-by":"crossref","first-page":"1481","DOI":"10.1126\/science.1252254","article-title":"Foundations of human reasoning in the prefrontal cortex","volume":"344","author":"Donoso","year":"2014","journal-title":"Science"},{"key":"10.1016\/j.neunet.2022.03.015_b12","series-title":"Handbook of nonlinear filtering, Vol. 12","first-page":"3","article-title":"A tutorial on particle filtering and smoothing: Fifteen years later","author":"Doucet","year":"2009"},{"key":"10.1016\/j.neunet.2022.03.015_b13","series-title":"2018 IEEE\/RSJ international conference on intelligent robots and systems (IROS)","first-page":"1577","article-title":"Learning actionable representations from visual observations","author":"Dwibedi","year":"2018"},{"issue":"1","key":"10.1016\/j.neunet.2022.03.015_b14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-017-01874-w","article-title":"Feature-based learning improves adaptability without compromising precision","volume":"8","author":"Farashahi","year":"2017","journal-title":"Nature Communications"},{"issue":"4","key":"10.1016\/j.neunet.2022.03.015_b15","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1109\/TPAMI.2006.79","article-title":"One-shot learning of object categories","volume":"28","author":"Fei-Fei","year":"2006","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2022.03.015_b16","series-title":"Learning visual feature spaces for robotic manipulation with deep spatial autoencoders","author":"Finn","year":"2015"},{"issue":"4","key":"10.1016\/j.neunet.2022.03.015_b17","doi-asserted-by":"crossref","DOI":"10.1098\/rsfs.2018.0013","article-title":"The functional neuroanatomy of face perception: from brain measurements to deep neural networks","volume":"8","author":"Grill-Spector","year":"2018","journal-title":"Interface Focus"},{"key":"10.1016\/j.neunet.2022.03.015_b18","series-title":"Towards a definition of disentangled representations","author":"Higgins","year":"2018"},{"key":"10.1016\/j.neunet.2022.03.015_b19","series-title":"Beta-vae: Learning basic visual concepts with a constrained variational framework","author":"Higgins","year":"2016"},{"key":"10.1016\/j.neunet.2022.03.015_b20","series-title":"Darla: Improving zero-shot transfer in reinforcement learning","author":"Higgins","year":"2017"},{"issue":"8","key":"10.1016\/j.neunet.2022.03.015_b21","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"key":"10.1016\/j.neunet.2022.03.015_b22","series-title":"International conference on machine learning","first-page":"2117","article-title":"Deep variational reinforcement learning for POMDPs","author":"Igl","year":"2018"},{"key":"10.1016\/j.neunet.2022.03.015_b23","series-title":"International conference on machine learning","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"Iqbal","year":"2019"},{"key":"10.1016\/j.neunet.2022.03.015_b24","series-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"Jaderberg","year":"2016"},{"key":"10.1016\/j.neunet.2022.03.015_b25","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.neubiorev.2014.06.001","article-title":"Bayesian modeling of flexible cognitive control","volume":"46","author":"Jiang","year":"2014","journal-title":"Neuroscience & Biobehavioral Reviews"},{"key":"10.1016\/j.neunet.2022.03.015_b26","unstructured":"Jones, M., & Canas, F. (2010). Integrating reinforcement learning with models of representation learning. In Proceedings of the annual meeting of the cognitive science society."},{"issue":"1655","key":"10.1016\/j.neunet.2022.03.015_b27","article-title":"An evolutionary computational theory of prefrontal executive function in decision-making","volume":"369","author":"Koechlin","year":"2014","journal-title":"Philosophical Transactions of the Royal Society, Series B (Biological Sciences)"},{"key":"10.1016\/j.neunet.2022.03.015_b28","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.neunet.2022.03.015_b29","doi-asserted-by":"crossref","DOI":"10.1017\/S0140525X16001837","article-title":"Building machines that learn and think like people","volume":"40","author":"Lake","year":"2017","journal-title":"Behavioral and Brain Sciences"},{"key":"10.1016\/j.neunet.2022.03.015_b30","series-title":"The 2010 international joint conference on neural networks (IJCNN)","first-page":"1","article-title":"Deep auto-encoder neural networks in reinforcement learning","author":"Lange","year":"2010"},{"key":"10.1016\/j.neunet.2022.03.015_b31","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.38105","article-title":"How biological attention mechanisms improve task performance in a large-scale visual system model","volume":"7","author":"Lindsay","year":"2018","journal-title":"eLife"},{"issue":"4","key":"10.1016\/j.neunet.2022.03.015_b32","first-page":"1580","article-title":"Attentional inertia and delayed orienting of spatial attention in task-switching","volume":"40","author":"Longman","year":"2014","journal-title":"Journal of Experimental Psychology: Human Perception and Performance"},{"key":"10.1016\/j.neunet.2022.03.015_b33","series-title":"Discriminative particle filter reinforcement learning for complex partial observations","author":"Ma","year":"2020"},{"issue":"4","key":"10.1016\/j.neunet.2022.03.015_b34","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1037\/h0076778","article-title":"A theory of attention: Variations in the associability of stimuli with reinforcement","volume":"82","author":"Mackintosh","year":"1975","journal-title":"Psychological Review"},{"key":"10.1016\/j.neunet.2022.03.015_b35","series-title":"International conference on neural information processing","first-page":"223","article-title":"Reinforcement learning with attention that works: A self-supervised approach","author":"Manchin","year":"2019"},{"issue":"1","key":"10.1016\/j.neunet.2022.03.015_b36","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1146\/annurev.neuro.24.1.167","article-title":"An integrative theory of prefrontal cortex function","volume":"24","author":"Miller","year":"2001","journal-title":"Annual Review of Neuroscience"},{"key":"10.1016\/j.neunet.2022.03.015_b37","series-title":"International conference on machine learning","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016"},{"issue":"7540","key":"10.1016\/j.neunet.2022.03.015_b38","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"10.1016\/j.neunet.2022.03.015_b39","series-title":"Advances in neural information processing systems","first-page":"12329","article-title":"Towards interpretable reinforcement learning using attention augmented agents","author":"Mott","year":"2019"},{"key":"10.1016\/j.neunet.2022.03.015_b40","series-title":"Visual reinforcement learning with imagined goals","author":"Nair","year":"2018"},{"issue":"21","key":"10.1016\/j.neunet.2022.03.015_b41","doi-asserted-by":"crossref","first-page":"8145","DOI":"10.1523\/JNEUROSCI.2978-14.2015","article-title":"Reinforcement learning in multidimensional environments relies on attention mechanisms","volume":"35","author":"Niv","year":"2015","journal-title":"Journal of Neuroscience"},{"key":"10.1016\/j.neunet.2022.03.015_b42","doi-asserted-by":"crossref","first-page":"545","DOI":"10.3389\/fnins.2017.00545","article-title":"Top-down control of visual attention by the prefrontal cortex. functional specialization and long-range interactions","volume":"11","author":"Paneri","year":"2017","journal-title":"Frontiers in Neuroscience"},{"key":"10.1016\/j.neunet.2022.03.015_b43","series-title":"International conference on machine learning","first-page":"7487","article-title":"Stabilizing transformers for reinforcement learning","author":"Parisotto","year":"2020"},{"issue":"4","key":"10.1016\/j.neunet.2022.03.015_b44","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1016\/j.tics.2019.01.010","article-title":"Holistic reinforcement learning: the role of structure and attention","volume":"23","author":"Radulescu","year":"2019","journal-title":"Trends in Cognitive Sciences"},{"key":"10.1016\/j.neunet.2022.03.015_b45","series-title":"2019 conference on cognitive computational neuroscience","article-title":"A particle filtering account of selective attention during learning","author":"Radulescu","year":"2019"},{"issue":"2","key":"10.1016\/j.neunet.2022.03.015_b46","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1016\/j.neuron.2009.01.002","article-title":"The normalization model of attention","volume":"61","author":"Reynolds","year":"2009","journal-title":"Neuron"},{"key":"10.1016\/j.neunet.2022.03.015_b47","series-title":"Advances in child development and behavior, Vol. 32","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1016\/S0065-2407(04)80007-7","article-title":"Attentional inertia in children\u2019s extended looking at television","author":"Richards","year":"2004"},{"key":"10.1016\/j.neunet.2022.03.015_b48","series-title":"AIP conference proceedings, Vol. 2181","article-title":"Algorithms and programs of suboptimal nonlinear filtering for Markov processes","author":"Rudenko","year":"2019"},{"issue":"7","key":"10.1016\/j.neunet.2022.03.015_b49","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1038\/nn876","article-title":"Global effects of feature-based attention in human visual cortex","volume":"5","author":"Saenz","year":"2002","journal-title":"Nature Neuroscience"},{"key":"10.1016\/j.neunet.2022.03.015_b50","article-title":"Brain-score: Which artificial neural network for object recognition is most brain-like?","author":"Schrimpf","year":"2018","journal-title":"BioRxiv"},{"issue":"1","key":"10.1016\/j.neunet.2022.03.015_b51","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1017\/S0140525X98000107","article-title":"The development of features in object concepts","volume":"21","author":"Schyns","year":"1998","journal-title":"Behavioral and Brain Sciences"},{"key":"10.1016\/j.neunet.2022.03.015_b52","series-title":"Proceedings of the 2019 4th international conference on mathematics and artificial intelligence","first-page":"71","article-title":"Self-attention for deep reinforcement learning","author":"Shen","year":"2019"},{"issue":"13","key":"10.1016\/j.neunet.2022.03.015_b53","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1037\/h0093825","article-title":"Learning and memorization of classifications","volume":"75","author":"Shepard","year":"1961","journal-title":"Psychological Monographs: General and Applied"},{"key":"10.1016\/j.neunet.2022.03.015_b54","series-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"10.1016\/j.neunet.2022.03.015_b55","series-title":"Curl: Contrastive unsupervised representations for reinforcement learning","author":"Srinivas","year":"2020"},{"key":"10.1016\/j.neunet.2022.03.015_b56","series-title":"Reinforcement learning: An introduction","author":"Sutton","year":"1998"},{"issue":"4","key":"10.1016\/j.neunet.2022.03.015_b57","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1016\/S0959-4388(03)00105-3","article-title":"Visual attention: the where, what, how and why of saliency","volume":"13","author":"Treue","year":"2003","journal-title":"Current Opinion in Neurobiology"},{"issue":"6736","key":"10.1016\/j.neunet.2022.03.015_b58","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1038\/21176","article-title":"Feature-based attention influences motion processing gain in macaque visual cortex","volume":"399","author":"Treue","year":"1999","journal-title":"Nature"},{"key":"10.1016\/j.neunet.2022.03.015_b59","series-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"issue":"7782","key":"10.1016\/j.neunet.2022.03.015_b60","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grandmaster level in StarCraft II using multi-agent reinforcement learning","volume":"575","author":"Vinyals","year":"2019","journal-title":"Nature"},{"key":"10.1016\/j.neunet.2022.03.015_b61","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2020.105910","article-title":"ADRL: An attention-based deep reinforcement learning framework for knowledge graph reasoning","volume":"197","author":"Wang","year":"2020","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2022.03.015_b62","doi-asserted-by":"crossref","first-page":"189","DOI":"10.3389\/fnhum.2011.00189","article-title":"Inferring relevance in a changing world","volume":"5","author":"Wilson","year":"2012","journal-title":"Frontiers in Human Neuroscience"},{"key":"10.1016\/j.neunet.2022.03.015_b63","series-title":"Improving sample efficiency in model-free reinforcement learning from images","author":"Yarats","year":"2019"},{"key":"10.1016\/j.neunet.2022.03.015_b64","series-title":"An initial attempt of combining visual selective attention with deep reinforcement learning","author":"Yuezhang","year":"2018"},{"key":"10.1016\/j.neunet.2022.03.015_b65","series-title":"Relational deep reinforcement learning","author":"Zambaldi","year":"2018"},{"key":"10.1016\/j.neunet.2022.03.015_b66","article-title":"Finite-time asynchronous dissipative filtering of conic-type nonlinear Markov jump systems","author":"Zhang","year":"2021","journal-title":"Science China. Information Sciences"},{"key":"10.1016\/j.neunet.2022.03.015_b67","article-title":"Asynchronous fault detection for interval type-2 fuzzy nonhomogeneous higher-level Markov jump systems with uncertain transition probabilities","author":"Zhang","year":"2021","journal-title":"IEEE Transactions on Fuzzy Systems"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608022000934?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608022000934?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2022,7,2]],"date-time":"2022-07-02T20:29:00Z","timestamp":1656793740000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608022000934"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":67,"alternative-id":["S0893608022000934"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2022.03.015","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2022,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Selective particle attention: Rapidly and flexibly selecting features for deep reinforcement learning","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2022.03.015","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2022 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}]}}