{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T22:26:26Z","timestamp":1747866386095,"version":"3.40.3"},"publisher-location":"Cham","reference-count":73,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030629991"},{"type":"electronic","value":"9783030630003"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-63000-3_1","type":"book-chapter","created":{"date-parts":[[2020,11,30]],"date-time":"2020-11-30T00:03:23Z","timestamp":1606694603000},"page":"3-22","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Adaptive Coordination of Multiple Learning Strategies in Brains and Robots"],"prefix":"10.1007","author":[{"given":"Mehdi","family":"Khamassi","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,30]]},"reference":[{"issue":"3","key":"1_CR1","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1109\/TNN.2004.826221","volume":"15","author":"A Arleo","year":"2004","unstructured":"Arleo, A., Smeraldi, F., Gerstner, W.: Cognitive navigation based on nonuniform Gabor space sampling, unsupervised growing networks, and reinforcement learning. IEEE Trans. Neural Netw. 15(3), 639\u2013652 (2004). https:\/\/doi.org\/10.1109\/TNN.2004.826221","journal-title":"IEEE Trans. Neural Netw."},{"key":"1_CR2","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1007\/978-3-642-33093-3_29","volume-title":"From Animals to Animats 12","author":"J Bellot","year":"2012","unstructured":"Bellot, J., Sigaud, O., Khamassi, M.: Which temporal difference learning algorithm best reproduces dopamine activity in a multi-choice task? In: Ziemke, T., Balkenius, C., Hallam, J. (eds.) SAB 2012. LNCS (LNAI), vol. 7426, pp. 289\u2013298. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33093-3_29"},{"key":"1_CR3","unstructured":"Bellot, J., Sigaud, O., Roesch, M.R., Schoenbaum, G., Girard, B., Khamassi, M.: Dopamine neurons activity in a multi-choice task: reward prediction error or value function? In: Proceedings of the French Computational Neuroscience NeuroComp12 Workshop, pp. 1\u20137 (2012)"},{"issue":"4","key":"1_CR4","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1016\/S0896-6273(02)00830-9","volume":"35","author":"N Burgess","year":"2002","unstructured":"Burgess, N., Maguire, E.A., O\u2019Keefe, J.: The human hippocampus and spatial and episodic memory. Neuron 35(4), 625\u2013641 (2002)","journal-title":"Neuron"},{"key":"1_CR5","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1007\/978-3-642-31525-1_6","volume-title":"Biomimetic and Biohybrid Systems","author":"K Caluwaerts","year":"2012","unstructured":"Caluwaerts, K., et al.: Neuro-inspired navigation strategies shifting for robots: integration of a multiple landmark taxon strategy. In: Prescott, T.J., Lepora, N.F., Mura, A., Verschure, P.F.M.J. (eds.) Living Machines 2012. LNCS (LNAI), vol. 7375, pp. 62\u201373. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-31525-1_6"},{"key":"1_CR6","doi-asserted-by":"publisher","first-page":"025009","DOI":"10.1088\/1748-3182\/7\/2\/025009","volume":"7","author":"K Caluwaerts","year":"2012","unstructured":"Caluwaerts, K., et al.: A biologically inspired meta-control navigation system for the Psikharpax rat robot. Bioinspiration Biomim. 7, 025009 (2012)","journal-title":"Bioinspiration Biomim."},{"key":"1_CR7","unstructured":"Cassandra, A.R., Kaelbling, L.P., Littman, M.L.: Acting optimally in partially observable stochastic domains. In: AAAI, vol. 94, pp. 1023\u20131028 (1994)"},{"issue":"6","key":"1_CR8","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.: Hippocampal replays under the scrutiny of reinforcement learning models. J. Neurophysiol. 120(6), 2877\u20132896 (2018)","journal-title":"J. Neurophysiol."},{"issue":"1","key":"1_CR9","doi-asserted-by":"publisher","first-page":"88","DOI":"10.3389\/frobt.2018.00088","volume":"5","author":"R Chatila","year":"2018","unstructured":"Chatila, R., et al.: Toward self-aware robots. Front. Robot. AI 5(1), 88\u2013108 (2018)","journal-title":"Front. Robot. AI"},{"key":"1_CR10","unstructured":"Chebotar, Y., Hausman, K., Zhang, M., Sukhatme, G., Schaal, S., Levine, S.: Combining model-based and model-free updates for trajectory-centric reinforcement learning. arXiv preprint arXiv:1703.03078 (2017)"},{"issue":"1\u20132","key":"1_CR11","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.bbr.2003.09.025","volume":"146","author":"E Coutureau","year":"2003","unstructured":"Coutureau, E., Killcross, S.: Inactivation of the infralimbic prefrontal cortex reinstates goal-directed responding in overtrained rats. Behav. Brain Res. 146(1\u20132), 167\u2013174 (2003)","journal-title":"Behav. Brain Res."},{"issue":"6","key":"1_CR12","doi-asserted-by":"publisher","first-page":"1204","DOI":"10.1016\/j.neuron.2011.02.027","volume":"69","author":"ND Daw","year":"2011","unstructured":"Daw, N.D., Gershman, S.J., Seymour, B., Dayan, P., Dolan, R.J.: Model-based influences on humans\u2019 choices and striatal prediction errors. Neuron 69(6), 1204\u20131215 (2011)","journal-title":"Neuron"},{"issue":"12","key":"1_CR13","doi-asserted-by":"publisher","first-page":"1704","DOI":"10.1038\/nn1560","volume":"8","author":"ND Daw","year":"2005","unstructured":"Daw, N.D., Niv, Y., Dayan, P.: Uncertainty-based competition between prefrontal and dorsolateral striatal systems for behavioral control. Nat. Neurosci. 8(12), 1704\u20131711 (2005)","journal-title":"Nat. Neurosci."},{"issue":"4","key":"1_CR14","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1162\/neco.1993.5.4.613","volume":"5","author":"P Dayan","year":"1993","unstructured":"Dayan, P.: Improving generalization for temporal difference learning: the successor representation. Neural Comput. 5(4), 613\u2013624 (1993)","journal-title":"Neural Comput."},{"issue":"6","key":"1_CR15","doi-asserted-by":"publisher","first-page":"848","DOI":"10.1177\/0956797616639301","volume":"27","author":"JH Decker","year":"2016","unstructured":"Decker, J.H., Otto, A.R., Daw, N.D., Hartley, C.A.: From creatures of habit to goal-directed learners: tracking the developmental emergence of model-based reinforcement learning. Psychol. Sci. 27(6), 848\u2013858 (2016)","journal-title":"Psychol. Sci."},{"issue":"7","key":"1_CR16","doi-asserted-by":"publisher","first-page":"1036","DOI":"10.1111\/j.1460-9568.2012.08050.x","volume":"35","author":"A Dezfouli","year":"2012","unstructured":"Dezfouli, A., Balleine, B.W.: Habits, action sequences and reinforcement learning. Eur. J. Neurosci. 35(7), 1036\u20131051 (2012)","journal-title":"Eur. J. Neurosci."},{"issue":"1","key":"1_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3758\/BF03199951","volume":"22","author":"A Dickinson","year":"1994","unstructured":"Dickinson, A., Balleine, B.: Motivational control of goal-directed action. Anim. Learn. Behav. 22(1), 1\u201318 (1994)","journal-title":"Anim. Learn. Behav."},{"issue":"4","key":"1_CR18","doi-asserted-by":"publisher","first-page":"e1006092","DOI":"10.1371\/journal.pcbi.1006092","volume":"14","author":"L Doll\u00e9","year":"2018","unstructured":"Doll\u00e9, L., Chavarriaga, R., Guillot, A., Khamassi, M.: Interactions of spatial strategies producing generalization gradient and blocking: a computational approach. PLoS Comput. Biol. 14(4), e1006092 (2018)","journal-title":"PLoS Comput. Biol."},{"key":"1_CR19","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/978-3-540-87601-4_8","volume-title":"Spatial Cognition VI. Learning, Reasoning, and Talking about Space","author":"L Doll\u00e9","year":"2008","unstructured":"Doll\u00e9, L., Khamassi, M., Girard, B., Guillot, A., Chavarriaga, R.: Analyzing interactions between navigation strategies using a computational model of action selection. In: Freksa, C., Newcombe, N.S., G\u00e4rdenfors, P., W\u00f6lfl, S. (eds.) Spatial Cognition 2008. LNCS (LNAI), vol. 5248, pp. 71\u201386. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-87601-4_8"},{"issue":"4","key":"1_CR20","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/s00422-010-0400-z","volume":"103","author":"L Doll\u00e9","year":"2010","unstructured":"Doll\u00e9, L., Sheynikhovich, D., Girard, B., Chavarriaga, R., Guillot, A.: Path planning versus cue responding: a bio-inspired model of switching between navigation strategies. Biol. Cybern. 103(4), 299\u2013317 (2010)","journal-title":"Biol. Cybern."},{"key":"1_CR21","unstructured":"Doncieux, S., et al.: Dream architecture: a developmental approach to open-ended learning in robotics. arXiv preprint arXiv:2005.06223 (2020)"},{"issue":"1","key":"1_CR22","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1162\/089976600300015961","volume":"12","author":"K Doya","year":"2000","unstructured":"Doya, K.: Reinforcement learning in continuous time and space. Neural Comput. 12(1), 219\u2013245 (2000)","journal-title":"Neural Comput."},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Dromnelle, R., Girard, B., Renaudo, E., Chatila, R., Khamassi, M.: Coping with the variability in humans reward during simulated human-robot interactions through the coordination of multiple learning strategies. In: Proceedings of the 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2020), Naples, Italy (2020)","DOI":"10.1109\/RO-MAN47096.2020.9223451"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Dromnelle, R., Renaudo, E., Pourcel, G., Chatila, R., Girard, B., Khamassi, M.: How to reduce computation time while sparing performance during robot navigation? A neuro-inspired architecture for autonomous shifting between model-based and model-free learning. In: 9th International Conference on Biomimetic & Biohybrid Systems (Living Machines 2020). pp. 1\u201312. LNAI, Online Conference (Initially Planned in Freiburg, Germany) (2020)","DOI":"10.1007\/978-3-030-64313-3_8"},{"issue":"9","key":"1_CR25","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1038\/nrn.2017.74","volume":"18","author":"H Eichenbaum","year":"2017","unstructured":"Eichenbaum, H.: Prefrontal-hippocampal interactions in episodic memory. Nat. Rev. Neurosci. 18(9), 547\u2013558 (2017)","journal-title":"Nat. Rev. Neurosci."},{"issue":"2","key":"1_CR26","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1038\/nrn1607","volume":"6","author":"PW Frankland","year":"2005","unstructured":"Frankland, P.W., Bontempi, B.: The organization of recent and remote memories. Nat. Rev. Neurosci. 6(2), 119\u2013130 (2005)","journal-title":"Nat. Rev. Neurosci."},{"issue":"5","key":"1_CR27","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1016\/j.neuron.2010.01.034","volume":"65","author":"AS Gupta","year":"2010","unstructured":"Gupta, A.S., van der Meer, M.A., Touretzky, D.S., Redish, A.D.: Hippocampal replay is not a simple function of experience. Neuron 65(5), 695\u2013705 (2010)","journal-title":"Neuron"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Hafez, M.B., Weber, C., Kerzel, M., Wermter, S.: Curious meta-controller: adaptive alternation between model-based and model-free control in deep reinforcement learning. In: 2019 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2019)","DOI":"10.1109\/IJCNN.2019.8852254"},{"key":"1_CR29","unstructured":"Hangl, S., Dunjko, V., Briegel, H.J., Piater, J.: Skill learning by autonomous robotic playing using active learning and creativity. arXiv preprint arXiv:1706.08560 (2017)"},{"key":"1_CR30","doi-asserted-by":"publisher","first-page":"16","DOI":"10.3389\/fnbot.2013.00016","volume":"7","author":"A Jauffret","year":"2013","unstructured":"Jauffret, A., Cuperlier, N., Gaussier, P., Tarroux, P.: From self-assessment to frustration, a small step toward autonomy in robotic navigation. Front. Neurorobotics 7, 16 (2013)","journal-title":"Front. Neurorobotics"},{"issue":"5445","key":"1_CR31","doi-asserted-by":"publisher","first-page":"1745","DOI":"10.1126\/science.286.5445.1745","volume":"286","author":"MS Jog","year":"1999","unstructured":"Jog, M.S., Kubota, Y., Connolly, C.I., Hillegaart, V., Graybiel, A.M.: Building neural representations of habits. Science 286(5445), 1745\u20131749 (1999)","journal-title":"Science"},{"issue":"45","key":"1_CR32","doi-asserted-by":"publisher","first-page":"12176","DOI":"10.1523\/JNEUROSCI.3761-07.2007","volume":"27","author":"A Johnson","year":"2007","unstructured":"Johnson, A., Redish, A.D.: Neural ensembles in CA3 transiently encode paths forward of the animal at a decision point. J. Neurosci. 27(45), 12176\u201312189 (2007)","journal-title":"J. Neurosci."},{"key":"1_CR33","volume-title":"Thinking, Fast and Slow","author":"D Kahneman","year":"2011","unstructured":"Kahneman, D.: Thinking, Fast and Slow. Macmillan, New York (2011)"},{"issue":"5","key":"1_CR34","doi-asserted-by":"publisher","first-page":"e1002055","DOI":"10.1371\/journal.pcbi.1002055","volume":"7","author":"M Keramati","year":"2011","unstructured":"Keramati, M., Dezfouli, A., Piray, P.: Speed\/accuracy trade-off between the habitual and the goal-directed processes. PLoS Comput. Biol. 7(5), e1002055 (2011)","journal-title":"PLoS Comput. Biol."},{"key":"1_CR35","unstructured":"Khamassi, M.: Complementary roles of the rat prefrontal cortex and striatum in reward-based learning and shifting navigation strategies. Ph.D. thesis, Universit\u00e9 Pierre et Marie Curie-Paris VI (2007)"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Khamassi, M., Girard, B.: Modeling awake hippocampal reactivations with model-based bidirectional search. Biol. Cybern. (114), 231\u2013248 (2020)","DOI":"10.1007\/s00422-020-00817-x"},{"key":"1_CR37","doi-asserted-by":"publisher","first-page":"79","DOI":"10.3389\/fnbeh.2012.00079","volume":"6","author":"M Khamassi","year":"2012","unstructured":"Khamassi, M., Humphries, M.D.: Integrating cortico-limbic-basal ganglia architectures for learning model-based and model-free navigation strategies. Front. Behav. Neurosci. 6, 79 (2012)","journal-title":"Front. Behav. Neurosci."},{"issue":"4","key":"1_CR38","doi-asserted-by":"publisher","first-page":"881","DOI":"10.1109\/TCDS.2018.2843122","volume":"10","author":"M Khamassi","year":"2018","unstructured":"Khamassi, M., Velentzas, G., Tsitsimis, T., Tzafestas, C.: Robot fast adaptation to changes in human engagement during simulated dynamic social interaction with active exploration in parameterized reinforcement learning. IEEE Trans. Cogn. Dev. Syst. 10(4), 881\u2013893 (2018)","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"issue":"4","key":"1_CR39","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1093\/cercor\/13.4.400","volume":"13","author":"S Killcross","year":"2003","unstructured":"Killcross, S., Coutureau, E.: Coordination of actions and habits in the medial prefrontal cortex of rats. Cereb. Cortex 13(4), 400\u2013408 (2003)","journal-title":"Cereb. Cortex"},{"issue":"3","key":"1_CR40","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1016\/j.neuron.2013.11.028","volume":"81","author":"SW Lee","year":"2014","unstructured":"Lee, S.W., Shimojo, S., O\u2019Doherty, J.P.: Neural computations underlying arbitration between model-based and model-free learning. Neuron 81(3), 687\u2013699 (2014)","journal-title":"Neuron"},{"key":"1_CR41","doi-asserted-by":"publisher","unstructured":"Lesaint, F., Sigaud, O., Flagel, S.B., Robinson, T.E., Khamassi, M.: Modelling Individual differences in the form of Pavlovian conditioned approach responses: a dual learning systems approach with factored representations. PLoS Comp. Biol. 10(2) (2014). https:\/\/doi.org\/10.1371\/journal.pcbi.1003466","DOI":"10.1371\/journal.pcbi.1003466"},{"issue":"5734","key":"1_CR42","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1126\/science.1114037","volume":"309","author":"S Leutgeb","year":"2005","unstructured":"Leutgeb, S., Leutgeb, J.K., Barnes, C.A., Moser, E.I., McNaughton, B.L., Moser, M.B.: Independent codes for spatial and episodic memory in hippocampal neuronal ensembles. Science 309(5734), 619\u2013623 (2005)","journal-title":"Science"},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Llofriu, M., et al.: A computational model for a multi-goal spatial navigation task inspired by rodent studies. In: 2019 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2019)","DOI":"10.1109\/IJCNN.2019.8851852"},{"key":"1_CR44","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.neunet.2015.10.004","volume":"72","author":"G Maffei","year":"2015","unstructured":"Maffei, G., Santos-Pata, D., Marcos, E., S\u00e1nchez-Fibla, M., Verschure, P.F.: An embodied biologically constrained model of foraging: from classical and operant conditioning to adaptive real-world behavior in DAC-X. Neural Netw. 72, 88\u2013108 (2015)","journal-title":"Neural Netw."},{"issue":"11","key":"1_CR45","doi-asserted-by":"publisher","first-page":"1609","DOI":"10.1038\/s41593-018-0232-z","volume":"21","author":"MG Mattar","year":"2018","unstructured":"Mattar, M.G., Daw, N.D.: Prioritized memory access explains planning and hippocampal replay. Nat. Neurosci. 21(11), 1609\u20131617 (2018)","journal-title":"Nat. Neurosci."},{"issue":"3","key":"1_CR46","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1037\/0033-295X.102.3.419","volume":"102","author":"JL McClelland","year":"1995","unstructured":"McClelland, J.L., McNaughton, B.L., O\u2019Reilly, R.C.: Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory. Psychol. Rev. 102(3), 419 (1995)","journal-title":"Psychol. Rev."},{"issue":"4","key":"1_CR47","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1016\/j.robot.2004.09.018","volume":"50","author":"JA Meyer","year":"2005","unstructured":"Meyer, J.A., Guillot, A., Girard, B., Khamassi, M., Pirim, P., Berthoz, A.: The Psikharpax project: towards building an artificial rat. Robot. Auton. Syst. 50(4), 211\u2013223 (2005)","journal-title":"Robot. Auton. Syst."},{"key":"1_CR48","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.cobeha.2020.02.017","volume":"32","author":"I Momennejad","year":"2020","unstructured":"Momennejad, I.: Learning structures: predictive representations, replay, and generalization. Curr. Opin. Behav. Sci. 32, 155\u2013166 (2020)","journal-title":"Curr. Opin. Behav. Sci."},{"issue":"1","key":"1_CR49","first-page":"103","volume":"13","author":"AW Moore","year":"1993","unstructured":"Moore, A.W., Atkeson, C.G.: Prioritized sweeping: reinforcement learning with less data and less time. Mach. Learn. 13(1), 103\u2013130 (1993)","journal-title":"Mach. Learn."},{"key":"1_CR50","doi-asserted-by":"crossref","unstructured":"Nagabandi, A., Kahn, G., Fearing, R.S., Levine, S.: Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 7559\u20137566. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8463189"},{"issue":"5","key":"1_CR51","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1162\/089892901750363208","volume":"13","author":"H Nakahara","year":"2001","unstructured":"Nakahara, H., Doya, K., Hikosaka, O.: Parallel cortico-basal ganglia mechanisms for acquisition and execution of visuomotor sequences-a computational approach. J. Cogn. Neurosci. 13(5), 626\u2013647 (2001)","journal-title":"J. Cogn. Neurosci."},{"key":"1_CR52","doi-asserted-by":"crossref","unstructured":"O\u2019Doherty, J.P., Lee, S., Tadayonnejad, R., Cockburn, J., Iigaya, K., Charpentier, C.J.: Why and how the brain weights contributions from a mixture of experts (2020)","DOI":"10.31234\/osf.io\/ns6kq"},{"key":"1_CR53","unstructured":"O\u2019keefe, J., Nadel, L.: The Hippocampus as a Cognitive Map. Clarendon Press, Oxford (1978)"},{"issue":"34","key":"1_CR54","doi-asserted-by":"publisher","first-page":"7763","DOI":"10.1523\/JNEUROSCI.1921-05.2005","volume":"25","author":"SB Ostlund","year":"2005","unstructured":"Ostlund, S.B., Balleine, B.W.: Lesions of medial prefrontal cortex disrupt the acquisition but not the expression of goal-directed learning. J. Neurosci. 25(34), 7763\u20137770 (2005)","journal-title":"J. Neurosci."},{"issue":"1","key":"1_CR55","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1146\/annurev.neuro.25.112701.142937","volume":"25","author":"MG Packard","year":"2002","unstructured":"Packard, M.G., Knowlton, B.J.: Learning and memory functions of the basal ganglia. Annu. Rev. Neurosci. 25(1), 563\u2013593 (2002)","journal-title":"Annu. Rev. Neurosci."},{"issue":"4","key":"1_CR56","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1177\/105971239300100403","volume":"1","author":"J Peng","year":"1993","unstructured":"Peng, J., Williams, R.J.: Efficient learning and planning within the Dyna framework. Adapt. Behav. 1(4), 437\u2013454 (1993)","journal-title":"Adapt. Behav."},{"key":"1_CR57","doi-asserted-by":"publisher","first-page":"92","DOI":"10.3389\/fpsyg.2013.00092","volume":"4","author":"G Pezzulo","year":"2013","unstructured":"Pezzulo, G., Rigoli, F., Chersi, F.: The mixed instrumental controller: using value of information to combine habitual choice and mental simulation. Front. Psychol. 4, 92 (2013)","journal-title":"Front. Psychol."},{"key":"1_CR58","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/978-3-319-09435-9_22","volume-title":"Biomimetic and Biohybrid Systems","author":"E Renaudo","year":"2014","unstructured":"Renaudo, E., Girard, B., Chatila, R., Khamassi, M.: Design of a control architecture for habit learning in robots. In: Duff, A., Lepora, N.F., Mura, A., Prescott, T.J., Verschure, P.F.M.J. (eds.) Living Machines 2014. LNCS (LNAI), vol. 8608, pp. 249\u2013260. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-09435-9_22"},{"key":"1_CR59","doi-asserted-by":"crossref","unstructured":"Renaudo, E., Girard, B., Chatila, R., Khamassi, M.: Respective advantages and disadvantages of model-based and model-free reinforcement learning in a robotics neuro-inspired cognitive architecture. In: Biologically Inspired Cognitive Architectures BICA 2015, Lyon, France, pp. 178\u2013184 (2015)","DOI":"10.1016\/j.procs.2015.12.194"},{"key":"1_CR60","doi-asserted-by":"crossref","unstructured":"Renaudo, E., Girard, B., Chatila, R., Khamassi, M.: Which criteria for autonomously shifting between goal-directed and habitual behaviors in robots? In: 5th International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EPIROB), Providence, RI, USA, pp. 254\u2013260. (2015)","DOI":"10.1109\/DEVLRN.2015.7346152"},{"key":"1_CR61","doi-asserted-by":"crossref","unstructured":"Rojas-Castro, D.M., Revel, A., Menard, M.: Rhizome architecture: an adaptive neurobehavioral control architecture for cognitive mobile robots\u2019 application in a vision-based indoor robot navigation context. Int. J. Soc. Robot. (3), 1\u201330 (2020)","DOI":"10.1007\/s12369-019-00602-2"},{"key":"1_CR62","unstructured":"Ruvolo, P., Eaton, E.: ELLA: an efficient lifelong learning algorithm. In: International Conference on Machine Learning, pp. 507\u2013515 (2013)"},{"key":"1_CR63","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/978-3-319-42417-0_23","volume-title":"Biomimetic and Biohybrid Systems","author":"D Santos-Pata","year":"2016","unstructured":"Santos-Pata, D., Zucca, R., Verschure, P.F.M.J.: Navigate the unknown: implications of grid-cells \u201cMental Travel\u201d in vicarious trial and error. In: Lepora, N.F.F., Mura, A., Mangan, M., Verschure, P.F.M.J.F.M.J., Desmulliez, M., Prescott, T.J.J. (eds.) Living Machines 2016. LNCS (LNAI), vol. 9793, pp. 251\u2013262. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-42417-0_23"},{"key":"1_CR64","doi-asserted-by":"publisher","first-page":"1593","DOI":"10.1126\/science.275.5306.1593","volume":"275","author":"W Schultz","year":"1997","unstructured":"Schultz, W., Dayan, P., Montague, P.R.: A neural substrate of prediction and reward. Science 275, 1593\u20131599 (1997)","journal-title":"Science"},{"issue":"11","key":"1_CR65","doi-asserted-by":"publisher","first-page":"1643","DOI":"10.1038\/nn.4650","volume":"20","author":"KL Stachenfeld","year":"2017","unstructured":"Stachenfeld, K.L., Botvinick, M.M., Gershman, S.J.: The hippocampus as a predictive map. Nat. Neurosci. 20(11), 1643 (2017)","journal-title":"Nat. Neurosci."},{"key":"1_CR66","doi-asserted-by":"crossref","unstructured":"Stoianov, I., Maisto, D., Pezzulo, G.: The hippocampal formation as a hierarchical generative model supporting generative replay and continual learning. bioRxiv (2020)","DOI":"10.1101\/2020.01.16.908889"},{"key":"1_CR67","doi-asserted-by":"crossref","unstructured":"Sutton, R.S.: Integrated architectures for learning, planning, and reacting based on approximating dynamic programming. In: Proceedings of the Seventh International Conference on Machine Learning, pp. 216\u2013224 (1990)","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"1_CR68","volume-title":"Introduction to Reinforcement Learning","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning, 1st edn. MIT Press, Cambridge (1998)","edition":"1"},{"key":"1_CR69","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1007\/978-1-4615-5529-2_8","volume-title":"Learning to Learn","author":"S Thrun","year":"1998","unstructured":"Thrun, S.: Lifelong learning algorithms. In: Thrun, S., Pratt, L. (eds.) Learning to Learn, pp. 181\u2013209. Springer, Boston (1998). https:\/\/doi.org\/10.1007\/978-1-4615-5529-2_8"},{"key":"1_CR70","doi-asserted-by":"publisher","first-page":"225","DOI":"10.3389\/fnbeh.2015.00225","volume":"9","author":"G Viejo","year":"2015","unstructured":"Viejo, G., Khamassi, M., Brovelli, A., Girard, B.: Modeling choice and reaction time during arbitrary visuomotor learning through the coordination of adaptive working memory and reinforcement learning. Front. Behav. Neurosci. 9, 225 (2015)","journal-title":"Front. Behav. Neurosci."},{"issue":"3\u20134","key":"1_CR71","first-page":"279","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3\u20134), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"issue":"4","key":"1_CR72","doi-asserted-by":"publisher","first-page":"930","DOI":"10.1109\/TSMCB.2008.920231","volume":"38","author":"MA Wiering","year":"2008","unstructured":"Wiering, M.A., van Hasselt, H.: Ensemble algorithms in reinforcement learning. IEEE Trans. Syst. Man Cybern. Part B 38(4), 930\u2013936 (2008). https:\/\/doi.org\/10.1109\/TSMCB.2008.920231","journal-title":"IEEE Trans. Syst. Man Cybern. Part B"},{"key":"1_CR73","doi-asserted-by":"crossref","unstructured":"Wise, S.P.: The role of the basal ganglia in procedural memory. In: Seminars in Neuroscience, vol. 8, pp. 39\u201346. Elsevier (1996)","DOI":"10.1006\/smns.1996.0006"}],"container-title":["Lecture Notes in Computer Science","Theory and Practice of Natural Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-63000-3_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,15]],"date-time":"2021-04-15T20:56:33Z","timestamp":1618520193000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-63000-3_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030629991","9783030630003"],"references-count":73,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-63000-3_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"30 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The author declares that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure\/Conflict-of-Interest Statement"}},{"value":"TPNC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on the Theory and Practice of Natural Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taoyuan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taiwan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 December 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tpnc2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/irdta.eu\/tpnc2020\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"12","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"50% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"An invited paper is also included.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}