{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:54:05Z","timestamp":1750308845665,"version":"3.41.0"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319590714"},{"type":"electronic","value":"9783319590721"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"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":[[2017]]},"DOI":"10.1007\/978-3-319-59072-1_43","type":"book-chapter","created":{"date-parts":[[2017,5,30]],"date-time":"2017-05-30T02:41:58Z","timestamp":1496112118000},"page":"363-370","source":"Crossref","is-referenced-by-count":1,"title":["A Reinforcement Learning Method with Implicit Critics from a Bystander"],"prefix":"10.1007","author":[{"given":"Kao-Shing","family":"Hwang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi-Wei","family":"Hsieh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Cheng","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin-Ling","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,5,31]]},"reference":[{"key":"43_CR1","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"43_CR2","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaebling","year":"1996","unstructured":"Kaebling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. J. Artif. Intell. Res. 4, 237\u2013285 (1996)","journal-title":"J. Artif. Intell. Res."},{"key":"43_CR3","first-page":"874","volume":"1","author":"A Ayesh","year":"2004","unstructured":"Ayesh, A.: Emotionally motivated reinforcement learning based controller. IEEE Int. Conf. Syst. Man Cybernet. 1, 874\u2013878 (2004)","journal-title":"IEEE Int. Conf. Syst. Man Cybernet."},{"key":"43_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/978-3-540-72348-6_6","volume-title":"Artifical Intelligence for Human Computing","author":"J Broekens","year":"2007","unstructured":"Broekens, J.: Emotion and reinforcement: affective facial expressions facilitate robot learning. In: Huang, T.S., Nijholt, A., Pantic, M., Pentland, A. (eds.) Artifical Intelligence for Human Computing. LNCS, vol. 4451, pp. 113\u2013132. Springer, Heidelberg (2007). doi: 10.1007\/978-3-540-72348-6_6"},{"key":"43_CR5","doi-asserted-by":"crossref","unstructured":"Obayashi, M., Takuno, T., Kuremoto, T., Kobayashi, K.: An emotional model embedded reinforcement learning system. In: 2012 IEEE International Conference on Systems, Man, and Cybernetics (2012)","DOI":"10.1109\/ICSMC.2012.6377870"},{"key":"43_CR6","doi-asserted-by":"crossref","unstructured":"Sridharan, M.: Augmented Reinforcement learning for interaction with non-expert humans in agent domains. In: 2011 10th International Conference on Machine Learning and Applications and Workshops (ICMLA), vol. 1 (2011)","DOI":"10.1109\/ICMLA.2011.37"},{"key":"43_CR7","doi-asserted-by":"crossref","unstructured":"Thomaz, A.L., Hoffman, G., Breazeal, C.: Reinforcement learning with human teachers: understanding how people want to teach robots. In: The 15th IEEE International Symposium on Robot and Human Interactive Communication, September 2006","DOI":"10.1109\/ROMAN.2006.314459"},{"key":"43_CR8","doi-asserted-by":"crossref","unstructured":"Knox, W.B., Stone, P.: TAMER: training an agent manually via evaluative reinforcement. In: ICDL 2008 7th IEEE International Conference on Development and Learning (2008)","DOI":"10.1109\/DEVLRN.2008.4640845"},{"key":"43_CR9","unstructured":"Rosenthal, S., Biswas, J., Veloso, M.: An effective personal mobile robot agent through symbiotic human-robot interaction. In: International Conference on Autonomous Agents and Multiagent Systems, pp. 915\u2013922 (2010)"},{"key":"43_CR10","unstructured":"Watkins, C.J.C.H.: Learning from delayed rewards. Ph.D. thesis, Cambridge University (1989)"},{"key":"43_CR11","first-page":"834","volume":"13","author":"AG Batro","year":"1993","unstructured":"Batro, A.G., Sutton, R.S., Anderson, C.W.: Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Trans. Syst. Man Cybern. 13, 834\u2013846 (1993)","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"43_CR12","doi-asserted-by":"crossref","unstructured":"Sun, Y., Zhang, R.B., Zhang, Y.: Research on adaptive heuristic critic algorithms and its applications. In: Proceedings of the 4th World Congress on Intelligent Control and Automation, vol. 1, pp. 345\u2013349 (2002)","DOI":"10.1109\/WCICA.2002.1022126"},{"key":"43_CR13","unstructured":"Konda, V., Tsitsiklis, J.: Actor-critic algorithms. In: Advances in Neural Information Processing Systems (2000)"},{"key":"43_CR14","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1016\/0893-6080(90)90056-Q","volume":"3","author":"V Gullapalli","year":"1990","unstructured":"Gullapalli, V.: A stochastic reinforcement learning algorithm for learning real valued functions. Neural Netw. 3, 671\u2013692 (1990)","journal-title":"Neural Netw."},{"key":"43_CR15","doi-asserted-by":"crossref","unstructured":"Gullapalli, V.: Associative reinforcement learning of real valued functions. In: Proceedings of IEEE, System, Man, Cybernetics, Charlottesville, VA, October 1991","DOI":"10.1109\/ICSMC.1991.169893"},{"key":"43_CR16","doi-asserted-by":"crossref","first-page":"1415","DOI":"10.1109\/5.58323","volume":"78","author":"B Widrow","year":"1990","unstructured":"Widrow, B., Lehr, M.A.: 30 years of adaptive neural networks: perceptron, madaline, and backpropagation. Proc. IEEE 78, 1415\u20131442 (1990)","journal-title":"Proc. IEEE"},{"key":"43_CR17","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"43_CR18","doi-asserted-by":"crossref","unstructured":"Hinton, G., Osindero, S., The, Y.: A fast learning algorithm for deep belief nets. Neural Comput. (2006)","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"43_CR19","first-page":"3371","volume":"11","author":"P Vincent","year":"2010","unstructured":"Vincent, P., Larochelle, H., Lajoie, I.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. Arch. 11, 3371\u20133408 (2010)","journal-title":"J. Mach. Learn. Res. Arch."},{"key":"43_CR20","first-page":"37","volume":"27","author":"P Baldi","year":"2012","unstructured":"Baldi, P.: Autoencoders, unsupervised learning, and deep architectures. JMLR Workshop Conf. Proc. 27, 37\u201350 (2012)","journal-title":"JMLR Workshop Conf. Proc."}],"container-title":["Lecture Notes in Computer Science","Advances in Neural Networks - ISNN 2017"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-59072-1_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T21:01:31Z","timestamp":1750280491000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-59072-1_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319590714","9783319590721"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-59072-1_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}