{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T17:36:34Z","timestamp":1770140194086,"version":"3.49.0"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2021,2,9]],"date-time":"2021-02-09T00:00:00Z","timestamp":1612828800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,2,9]],"date-time":"2021-02-09T00:00:00Z","timestamp":1612828800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Biol Cybern"],"published-print":{"date-parts":[[2021,4]]},"DOI":"10.1007\/s00422-021-00862-0","type":"journal-article","created":{"date-parts":[[2021,2,10]],"date-time":"2021-02-10T05:18:04Z","timestamp":1612934284000},"page":"131-134","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Deep reinforcement learning to study spatial navigation, learning and memory in artificial and biological agents"],"prefix":"10.1007","volume":"115","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4937-1780","authenticated-orcid":false,"given":"Edgar","family":"Bermudez-Contreras","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,2,9]]},"reference":[{"key":"862_CR1","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/s00422-020-00829-7","volume":"114","author":"MA Arbib","year":"2020","unstructured":"Arbib MA (2020) From spatial navigation via visual construction to episodic memory and imagination. Biol Cybern 114:139\u2013167","journal-title":"Biol Cybern"},{"key":"862_CR2","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1038\/s41586-018-0102-6","volume":"26","author":"A Banino","year":"2018","unstructured":"Banino A, Barry C, Uria B, Blundell C, Lillicrap T, Mirowski P et al (2018) Vector-based navigation using grid-like representations in artificial agents. Nature 26:429\u2013433","journal-title":"Nature"},{"key":"862_CR3","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/s00422-020-00837-7","volume":"114","author":"L Benjamin","year":"2020","unstructured":"Benjamin L, Thomas PJ, Fellous JM (2020) A renewed vision for biological cybernetics. Biol Cybern 114:315\u2013316","journal-title":"Biol Cybern"},{"key":"862_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1117\/1.NPh.5.2.025005","volume":"5","author":"E Bermudez-Contreras","year":"2018","unstructured":"Bermudez-Contreras E, Chekhov S, Sun J, Tarnowsky J, McNaughton BL, Mohajerani MH (2018) High-performance, inexpensive setup for simultaneous multisite recording of electrophysiological signals and mesoscale voltage imaging in the mouse cortex. Neurophotonics 5:1","journal-title":"Neurophotonics"},{"key":"862_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3389\/fncom.2020.00063","volume":"14","author":"E Bermudez Contreras","year":"2020","unstructured":"Bermudez Contreras E, Clark BJ, Wilber A (2020) The neuroscience of spatial navigation and the relationship to artificial intelligence. Front Comput Neurosci 14:1\u201316","journal-title":"Front Comput Neurosci"},{"key":"862_CR6","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1016\/j.neuron.2020.06.014","volume":"107","author":"M Botvinick","year":"2020","unstructured":"Botvinick M, Wang JX, Dabney W, Miller KJ, Kurth-Nelson Z (2020) Deep reinforcement learning and its neuroscientific implications. Neuron 107:603\u2013616","journal-title":"Neuron"},{"key":"862_CR7","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1038\/nn.3304","volume":"16","author":"G Buzs\u00e1ki","year":"2013","unstructured":"Buzs\u00e1ki G, Moser EI (2013) Memory, navigation and theta rhythm in the hippocampal-entorhinal system. Nat Neurosci 16:130\u2013138","journal-title":"Nat Neurosci"},{"key":"862_CR8","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.1038\/s41593-018-0189-y","volume":"21","author":"MG Campbell","year":"2018","unstructured":"Campbell MG, Ocko SA, Mallory CS, Low IIC, Ganguli S, Giocomo LM (2018) Principles governing the integration of landmark and self-motion cues in entorhinal cortical codes for navigation. Nat Neurosci 21:1096\u20131106","journal-title":"Nat Neurosci"},{"key":"862_CR9","doi-asserted-by":"publisher","first-page":"2877","DOI":"10.1152\/jn.00145.2018","volume":"120","author":"R Caz\u00e9","year":"2018","unstructured":"Caz\u00e9 R, Khamassi M, Aubin L, Girard B (2018) Hippocampal replays under the scrutiny of reinforcement learning models. J Neurophysiol 120:2877\u20132896","journal-title":"J Neurophysiol"},{"key":"862_CR10","unstructured":"Cueva CJ, Wei X-X (2018) Emergence of grid-like representations by training recurrent neural networks to perform spatial localization. In: International conference on learning representations (ICLR), pp 1\u201319"},{"key":"862_CR11","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1038\/s41586-019-1924-6","volume":"577","author":"W Dabney","year":"2020","unstructured":"Dabney W, Kurth-Nelson Z, Uchida N, Starkweather CK, Hassabis D, Munos R et al (2020) A distributional code for value in dopamine-based reinforcement learning. Nature 577:671\u2013675","journal-title":"Nature"},{"key":"862_CR12","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/s00422-020-00832-y","volume":"114","author":"JM Fellous","year":"2020","unstructured":"Fellous JM, Dominey P, Weitzenfeld A (2020) Complex spatial navigation in animals, computational models and neuro-inspired robots. Biol Cybern 114:137\u2013138","journal-title":"Biol Cybern"},{"key":"862_CR13","unstructured":"Kanitscheider I, Fiete I (2017) Training recurrent networks to generate hypotheses about how the brain solves hard navigation problems. In: Advances in neural information processing Systems (NIPS), pp 4530\u20134539"},{"key":"862_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.7554\/eLife.32548","volume":"7","author":"I Momennejad","year":"2018","unstructured":"Momennejad I, Otto AR, Daw ND, Norman KA (2018) Offline replay supports planning in human reinforcement learning. Elife 7:1\u201325","journal-title":"Elife"},{"key":"862_CR15","doi-asserted-by":"publisher","first-page":"1761","DOI":"10.1038\/s41593-019-0520-2","volume":"22","author":"B Richards","year":"2019","unstructured":"Richards B, Lillicrap TP, Beaudoin P, Bengio Y, Bogacz R, Christensen A et al (2019) A deep learning framework for neuroscience. Nat Neurosci 22:1761\u20131770","journal-title":"Nat Neurosci"},{"key":"862_CR16","volume-title":"The wiley handbook of evolutionary neuroscience","year":"2017","unstructured":"Shepard SV (ed) (2017) The wiley handbook of evolutionary neuroscience. Wiley Blackwell, Chichester, West Sussex"},{"key":"862_CR17","first-page":"1","volume":"6","author":"HF Song","year":"2017","unstructured":"Song HF, Yang GR, Wang XJ (2017) Reward-based training of recurrent neural networks for cognitive and value-based tasks. Elife 6:1\u201324","journal-title":"Elife"},{"key":"862_CR18","unstructured":"Sorscher B, Mel GC, Ganguli S, Ocko SA (2019) A unified theory for the origin of grid cells through the lens of pattern formation. In: Advances in neural information processing systems (NeurIPS) (Vancouver, Canada), pp 1\u201311"},{"key":"862_CR19","volume-title":"Reinforcement learning. an introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton RS, Barto AG (2018) Reinforcement learning. an introduction, vol 2. MIT Press, Cambridge"},{"key":"862_CR20","doi-asserted-by":"publisher","first-page":"860","DOI":"10.1038\/s41593-018-0147-8","volume":"21","author":"JX Wang","year":"2018","unstructured":"Wang JX, Kurth-Nelson Z, Kumaran D, Tirumala D, Soyer H, Leibo JZ et al (2018) Prefrontal cortex as a meta-reinforcement learning system. Nat Neurosci 21:860\u2013868","journal-title":"Nat Neurosci"},{"key":"862_CR21","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1038\/nn.4244","volume":"19","author":"DLK Yamins","year":"2016","unstructured":"Yamins DLK, DiCarlo JJ (2016) Using goal-driven deep learning models to understand sensory cortex. Nat Neurosci 19:356\u2013365","journal-title":"Nat Neurosci"}],"container-title":["Biological Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00422-021-00862-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00422-021-00862-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00422-021-00862-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,10]],"date-time":"2021-04-10T12:22:03Z","timestamp":1618057323000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00422-021-00862-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,9]]},"references-count":21,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,4]]}},"alternative-id":["862"],"URL":"https:\/\/doi.org\/10.1007\/s00422-021-00862-0","relation":{},"ISSN":["0340-1200","1432-0770"],"issn-type":[{"value":"0340-1200","type":"print"},{"value":"1432-0770","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,9]]},"assertion":[{"value":"12 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 February 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}