{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T23:31:17Z","timestamp":1782862277875,"version":"3.54.5"},"reference-count":16,"publisher":"Springer Science and Business Media LLC","issue":"2-3","license":[{"start":{"date-parts":[[1996,5,1]],"date-time":"1996-05-01T00:00:00Z","timestamp":830908800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[1996,5,1]],"date-time":"1996-05-01T00:00:00Z","timestamp":830908800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Learning"],"published-print":{"date-parts":[[1996,5]]},"DOI":"10.1023\/a:1018237008823","type":"journal-article","created":{"date-parts":[[2003,2,6]],"date-time":"2003-02-06T17:07:14Z","timestamp":1044551234000},"page":"279-303","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Purposive Behavior Acquisition for a Real Robot by Vision-Based Reinforcement Learning"],"prefix":"10.1007","volume":"23","author":[{"given":"Minoru","family":"Asada","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shoichi","family":"Noda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sukoya","family":"Tawaratsumida","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Koh","family":"Hosoda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"114017_CR1","volume-title":"Dynamic Programming","author":"R. Bellman","year":"1957","unstructured":"Bellman, R. (1957). Dynamic Programming. Princeton University Press, Princeton, NJ."},{"key":"114017_CR2","unstructured":"Chapman, D. & Kaelbling, L. P. (1991). \"Input generalization in delayed reinforcement learning: An alogorithm and performance comparisons\". In Proc. of IJCAI-91, pages 726\u2013731."},{"key":"114017_CR3","doi-asserted-by":"crossref","unstructured":"Connel, J. H. & Mahadevan, S. editors (1993). Robot Learning. Kluwer Academic Publishers.","DOI":"10.1007\/978-1-4615-3184-5"},{"key":"114017_CR4","doi-asserted-by":"crossref","unstructured":"Connel, J. H. & Mahadevan, S. (1993). \"Rapid task learning for real robot\". In J. H. Connel and S. Mahadevan, editors, Robot Learning, chapter 5. Kluwer Academic Publishers.","DOI":"10.1007\/978-1-4615-3184-5_5"},{"key":"114017_CR5","doi-asserted-by":"crossref","unstructured":"Fagg, A. H., Lotspeich, D., & Bekey, G. A. (1994). \"A reinforcement learning approach to reactive control policy design for autonomous robots\". In Proc. of 1994 IEEE Int. Conf. on Robotics and Automation, pages 39\u201344.","DOI":"10.1109\/ROBOT.1994.351013"},{"key":"114017_CR6","unstructured":"Inaba, M. (1993). \"Remote-brained robotics: Interfacing ai with real world behaviors\". In Preprints of ISRR'93, Pitsuburg."},{"key":"114017_CR7","unstructured":"Kaelbling, L. P. (1993). \"Learning to achieve goals\". In Proc. of IJCAI-93, pages 1094\u20131098."},{"key":"114017_CR8","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1023\/A:1022628806385","volume":"8","author":"L. Lin","year":"1992","unstructured":"Lin, Long-Ji (1992). Self-improving reactive agents based on reinforcement learning, planning and teaching. Machine Learning, 8:293\u2013321.","journal-title":"Machine Learning"},{"key":"114017_CR9","unstructured":"Mahadevan, S. & Connell, J. (1991) \"Automatic programming of behavior-based robots using reinforcement learning\". In AAAI-'91, pages 768\u2013773."},{"key":"114017_CR10","doi-asserted-by":"crossref","unstructured":"Mataric, M. (1994). \"Reward functions for accelerated learning\". In Proc. of Conf. on Machine Learning-1994, pages 181\u2013189, 1994.","DOI":"10.1016\/B978-1-55860-335-6.50030-1"},{"key":"114017_CR11","doi-asserted-by":"crossref","unstructured":"Pomerleau, Dean A. (1993). Knowledge-based training of aritificial neural networks for autonomous robot driving. In J. H. Connel and S. Mahadevan, editors, Robot Learning, chapter 2. Kluwer Academic Publishers.","DOI":"10.1007\/978-1-4615-3184-5_2"},{"key":"114017_CR12","doi-asserted-by":"crossref","unstructured":"Saito, F. & Fukuda, T. (1994). \"Learning architecture for real robot systems-extension of connectionist q-learning for continuous robot control domain\". In Proc. of 1994 IEEE Int. Conf. on Robotics and Automation, pages 27\u201332.","DOI":"10.1109\/ROBOT.1994.351015"},{"key":"114017_CR13","unstructured":"Sutton, R. S. (1992). \"Special issue on reinforcement learning\". In R. S. Sutton(Guest), editor, Machine Learning, volume 8, pages-. Kluwer Academic Publishers."},{"key":"114017_CR14","unstructured":"Watkins, C. J. C. H. (1989). Learning from delayed rewards\". PhD thesis, King's College, University of Cambridge."},{"key":"114017_CR15","doi-asserted-by":"crossref","unstructured":"Whitehead, S. D. & Ballard, D. H. (1990). \"Active perception and reinforcement learning\". In Proc. of Workshop on Machine Learning-1990, pages 179\u2013188.","DOI":"10.1016\/B978-1-55860-141-3.50025-0"},{"key":"114017_CR16","unstructured":"Whitehead, S. D. (1991). \"A complexity analysis of cooperative mechanisms in reinforcement learning\". In Proc. AAAI-91, pages 607\u2013613."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1018237008823.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1018237008823\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1018237008823.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T11:39:12Z","timestamp":1752147552000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1018237008823"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1996,5]]},"references-count":16,"journal-issue":{"issue":"2-3","published-print":{"date-parts":[[1996,5]]}},"alternative-id":["114017"],"URL":"https:\/\/doi.org\/10.1023\/a:1018237008823","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[1996,5]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}