{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T07:26:28Z","timestamp":1725693988888},"reference-count":37,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2019,10,25]],"date-time":"2019-10-25T00:00:00Z","timestamp":1571961600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000268","name":"UK Biotechnology and Biological Sciences Research Council","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":[[2020,2]]},"DOI":"10.1016\/j.neunet.2019.10.011","type":"journal-article","created":{"date-parts":[[2019,10,26]],"date-time":"2019-10-26T05:42:55Z","timestamp":1572068575000},"page":"218-230","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":30,"special_numbering":"C","title":["A complementary learning systems approach to temporal difference learning"],"prefix":"10.1016","volume":"122","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.2019.10.011_b1","series-title":"The arcade learning environment : An evaluation platform for general agents","first-page":"253","author":"Bellemare","year":"2013"},{"key":"10.1016\/j.neunet.2019.10.011_b2","series-title":"Model-free episodic control","author":"Blundell","year":"2016"},{"key":"10.1016\/j.neunet.2019.10.011_b3","first-page":"1","article-title":"Reinforcement learning , fast and slow","author":"Botvinick","year":"2019","journal-title":"Trends in Cognitive Sciences"},{"issue":"4","key":"10.1016\/j.neunet.2019.10.011_b4","doi-asserted-by":"crossref","first-page":"3036","DOI":"10.1152\/jn.01211.2006","article-title":"Neural coding of reward-prediction error signals during classical conditioning with attractive faces","volume":"97","author":"Bray","year":"2007","journal-title":"Journal of Neurophysiology"},{"key":"10.1016\/j.neunet.2019.10.011_b5","series-title":"OpenAI gym","first-page":"1","author":"Brockman","year":"2016"},{"issue":"4","key":"10.1016\/j.neunet.2019.10.011_b6","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1016\/S0896-6273(02)00830-9","article-title":"The human hippocampus and spatial and episodic memory","volume":"35","author":"Burgess","year":"2002","journal-title":"Neuron"},{"issue":"2","key":"10.1016\/j.neunet.2019.10.011_b7","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1016\/S0896-6273(03)00169-7","article-title":"Temporal difference models and reward-related learning in the human brain","volume":"38","author":"Doherty","year":"2003","journal-title":"Neuron"},{"key":"10.1016\/j.neunet.2019.10.011_b8","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.neuropharm.2012.06.027","article-title":"Neuropharmacology Hippocampal long-term depression mediates spatial reversal learning in the Morris water maze","volume":"64","author":"Dong","year":"2013","journal-title":"Neuropharmacology"},{"key":"10.1016\/j.neunet.2019.10.011_b9","series-title":"An introduction to deep reinforcement learning","author":"Fran\u00e7ois-lavet","year":"2018"},{"key":"10.1016\/j.neunet.2019.10.011_b10","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1146\/annurev-psych-122414-033625","article-title":"Reinforcement learning and episodic memory in humans and animals : An integrative framework","volume":"68","author":"Gershman","year":"2017","journal-title":"Annual Review of Psychology"},{"key":"10.1016\/j.neunet.2019.10.011_b11","first-page":"249","article-title":"A model of how the basal ganglia generate and use neural signals that predict reinforcement","author":"Houk","year":"1995","journal-title":"Computational Neuroscience. Models of Information Processing in the Basal Ganglia"},{"issue":"45","key":"10.1016\/j.neunet.2019.10.011_b12","doi-asserted-by":"crossref","first-page":"12176","DOI":"10.1523\/JNEUROSCI.3761-07.2007","article-title":"Neural ensembles in CA3 transiently encode paths forward of the animal at a decision point","volume":"27","author":"Johnson","year":"2007","journal-title":"Journal of Neuroscience"},{"key":"10.1016\/j.neunet.2019.10.011_b13","series-title":"ViZDoom : A doom-based AI research platform for visual reinforcement learning","author":"Kempka","year":"2016"},{"key":"10.1016\/j.neunet.2019.10.011_b14","first-page":"10","article-title":"Actor-critic algorithms","author":"Konda","year":"2000","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"7","key":"10.1016\/j.neunet.2019.10.011_b15","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1016\/j.tics.2016.05.004","article-title":"What learning systems do intelligent agents need? Complementary learning systems theory updated","volume":"20","author":"Kumaran","year":"2016","journal-title":"Trends in Cognitive Sciences"},{"key":"10.1016\/j.neunet.2019.10.011_b16","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":"The Behavioral and Brain Sciences"},{"key":"10.1016\/j.neunet.2019.10.011_b17","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1146\/annurev-neuro-062111-150512","article-title":"Neural basis of reinforcement learning and decision making","volume":"35","author":"Lee","year":"2012","journal-title":"Annual Review of Neuroscience"},{"issue":"11","key":"10.1016\/j.neunet.2019.10.011_b18","doi-asserted-by":"crossref","first-page":"1609","DOI":"10.1038\/s41593-018-0232-z","article-title":"Prioritized memory access explains planning and hippocampal replay","volume":"21","author":"Mattar","year":"2018","journal-title":"Nature Neuroscience"},{"issue":"3","key":"10.1016\/j.neunet.2019.10.011_b19","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1037\/0033-295X.102.3.419","article-title":"Why there are complementary learning systems in the hippocampus and neocortex: Insights from the successes and failures of connectionist models of learning and memory","volume":"102","author":"McClelland","year":"1995","journal-title":"Psychological Review"},{"issue":"2","key":"10.1016\/j.neunet.2019.10.011_b20","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1016\/S0896-6273(03)00154-5","article-title":"Temporal prediction errors in a passive learning task activate human striatum","volume":"38","author":"Mcclure","year":"2003","journal-title":"Neuron"},{"key":"10.1016\/j.neunet.2019.10.011_b21","series-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016"},{"key":"10.1016\/j.neunet.2019.10.011_b22","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"},{"issue":"3","key":"10.1016\/j.neunet.2019.10.011_b23","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.jmp.2008.12.005","article-title":"Reinforcement learning in the brain","volume":"53","author":"Niv","year":"2009","journal-title":"Journal of Mathematical Psychology"},{"issue":"1","key":"10.1016\/j.neunet.2019.10.011_b24","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.cub.2017.10.073","article-title":"Review the role of hippocampal replay in memory and planning","volume":"28","author":"Olafsdottir","year":"2018","journal-title":"Current Biology"},{"issue":"10","key":"10.1016\/j.neunet.2019.10.011_b25","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1016\/j.tins.2011.08.001","article-title":"The hippocampal \u2013 striatal axis in learning, prediction and goal-directed behavior","volume":"34","author":"Pennartz","year":"2011","journal-title":"Trends in Neurosciences"},{"key":"10.1016\/j.neunet.2019.10.011_b26","series-title":"Neural episodic control","author":"Pritzel","year":"2017"},{"issue":"42","key":"10.1016\/j.neunet.2019.10.011_b27","doi-asserted-by":"crossref","first-page":"13365","DOI":"10.1523\/JNEUROSCI.2572-09.2009","article-title":"Rats deciding between differently delayed or sized rewards","volume":"29","author":"Roesch","year":"2009","journal-title":"Journal of Neuroscience"},{"issue":"9","key":"10.1016\/j.neunet.2019.10.011_b28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pcbi.1005768","article-title":"Predictive representations can link model-based reinforcement learning to model-free mechanisms","volume":"13","author":"Russek","year":"2017","journal-title":"PLoS Computational Biology"},{"issue":"1","key":"10.1016\/j.neunet.2019.10.011_b29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1152\/jn.1998.80.1.1","article-title":"Predictive reward signal of dopamine neurons","volume":"80","author":"Schultz","year":"1998","journal-title":"Journal of Neurophysiology"},{"issue":"1","key":"10.1016\/j.neunet.2019.10.011_b30","doi-asserted-by":"crossref","first-page":"23","DOI":"10.31887\/DCNS.2016.18.1\/wschultz","article-title":"Dopamine reward prediction error coding","volume":"18","author":"Schultz","year":"2016","journal-title":"Dialogues in Clinical Neuroscience"},{"issue":"12","key":"10.1016\/j.neunet.2019.10.011_b31","doi-asserted-by":"crossref","first-page":"4595","DOI":"10.1523\/JNEUROSCI.12-12-04595.1992","article-title":"Neuronal activity in monkey ventral striatum related to the expectation of reward","volume":"12","author":"Schultz","year":"1992","journal-title":"Journal of Neuroscience"},{"issue":"5306","key":"10.1016\/j.neunet.2019.10.011_b32","doi-asserted-by":"crossref","first-page":"1593","DOI":"10.1126\/science.275.5306.1593","article-title":"A neural substrate of prediction and reward","volume":"275","author":"Schultz","year":"1997","journal-title":"Science"},{"issue":"4","key":"10.1016\/j.neunet.2019.10.011_b33","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1016\/S0896-6273(03)00264-2","article-title":"Neural encoding in ventral striatum during olfactory discrimination learning","volume":"38","author":"Setlow","year":"2003","journal-title":"Neuron"},{"issue":"11","key":"10.1016\/j.neunet.2019.10.011_b34","doi-asserted-by":"crossref","first-page":"1643","DOI":"10.1038\/nn.4650","article-title":"The hippocampus as a predictive map","volume":"20","author":"Stachenfeld","year":"2017","journal-title":"Nature Neuroscience"},{"key":"10.1016\/j.neunet.2019.10.011_b35","series-title":"Reinforcement learning: An introduction","first-page":"1","author":"Sutton","year":"1998"},{"key":"10.1016\/j.neunet.2019.10.011_b36","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation richard","volume":"12","author":"Sutton","year":"2000","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"28","key":"10.1016\/j.neunet.2019.10.011_b37","doi-asserted-by":"crossref","first-page":"6686","DOI":"10.1523\/JNEUROSCI.3212-16.2017","article-title":"Unraveling the role of the hippocampus in reversal learning","volume":"37","author":"Vila-Ballo","year":"2017","journal-title":"Journal of Neuroscience"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608019303338?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608019303338?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2021,1,26]],"date-time":"2021-01-26T04:31:34Z","timestamp":1611635494000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608019303338"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2]]},"references-count":37,"alternative-id":["S0893608019303338"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2019.10.011","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2020,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A complementary learning systems approach to temporal difference learning","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2019.10.011","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2019 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}]}}