{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:07:14Z","timestamp":1761844034112},"publisher-location":"Berlin, Heidelberg","reference-count":9,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642175367"},{"type":"electronic","value":"9783642175374"}],"license":[{"start":{"date-parts":[[2010,1,1]],"date-time":"2010-01-01T00:00:00Z","timestamp":1262304000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-17537-4_27","type":"book-chapter","created":{"date-parts":[[2010,11,12]],"date-time":"2010-11-12T08:21:50Z","timestamp":1289550110000},"page":"215-222","source":"Crossref","is-referenced-by-count":4,"title":["Free-Energy Based Reinforcement Learning for Vision-Based Navigation with High-Dimensional Sensory Inputs"],"prefix":"10.1007","author":[{"given":"Stefan","family":"Elfwing","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Makoto","family":"Otsuka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eiji","family":"Uchibe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenji","family":"Doya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.: Reinforcement Learning: An Introduction (1998)","key":"27_CR1","DOI":"10.1109\/TNN.1998.712192"},{"key":"27_CR2","first-page":"1063","volume":"5","author":"B. Sallans","year":"2004","unstructured":"Sallans, B., Hinton, G.E.: Reinforcement learning with factored states and actions. Journal of Machine Learning Research\u00a05, 1063\u20131088 (2004)","journal-title":"Journal of Machine Learning Research"},{"unstructured":"Otsuka, M., Yoshimoto, J., Doya, K.: Free-energy-based reinforcement learning in apartially observable environments. In: Proceedings of ESANN, pp. 541\u2013545 (2010)","key":"27_CR3"},{"unstructured":"Shibata, K., Iida, M.: Acquisition of box pushing by direct-vision-based reinforce-ment learning. In: Proceedings of SICE 2003, vol.\u00a03, pp. 2322\u20132327 (2003)","key":"27_CR4"},{"key":"27_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1007\/978-3-642-02490-0_92","volume-title":"Advances in Neuro-Information Processing","author":"K. Shibata","year":"2009","unstructured":"Shibata, K., Kawano, T.: Learning of action generation from raw camera imagesin a real-world-like environment by simple coupling of reinforcement learning and a neural network. In: K\u00f6ppen, M., Kasabov, N., Coghill, G. (eds.) ICONIP 2008. LNCS, vol.\u00a05506, pp. 755\u2013762. Springer, Heidelberg (2009)"},{"unstructured":"Rummery, G.A., Niranjan, M.: On-line Q-learning using connectionist systems. Technical Report CUED\/F-INFENG\/TR 166, Cambridge University (1994)","key":"27_CR6"},{"unstructured":"Sutton, R.S.: Generalization in reinforcement learning: Successful examples using sparse coarse coding. In: NIPS 1995, pp. 1038\u20131044 (1996)","key":"27_CR7"},{"issue":"1-3","key":"27_CR8","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/BF00114726","volume":"22","author":"S.P. Singh","year":"1996","unstructured":"Singh, S.P., Sutton, R.S.: Reinforcement learning with replacing eligibility traces. Machine Learning\u00a022(1-3), 123\u2013158 (1996)","journal-title":"Machine Learning"},{"issue":"2","key":"27_CR9","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1177\/105971230501300206","volume":"13","author":"K. Doya","year":"2005","unstructured":"Doya, K., Uchibe, E.: The cyber rodent project: Exploration of adaptive mechanisms for self-preservation and self-reproduction. Adaptive Behavior\u00a013(2), 149\u2013160 (2005)","journal-title":"Adaptive Behavior"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing. Theory and Algorithms"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-17537-4_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,6]],"date-time":"2019-06-06T03:31:48Z","timestamp":1559791908000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-17537-4_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642175367","9783642175374"],"references-count":9,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-17537-4_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}