{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:19:14Z","timestamp":1725902354951},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319592930"},{"type":"electronic","value":"9783319592947"}],"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\/978-3-319-59294-7_15","type":"book-chapter","created":{"date-parts":[[2017,6,22]],"date-time":"2017-06-22T10:19:10Z","timestamp":1498126750000},"page":"172-186","source":"Crossref","is-referenced-by-count":1,"title":["Proposal of an Action Selection Strategy with Expected Failure Probability and Its Evaluation in Multi-agent Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Kazuteru","family":"Miyazaki","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Koudai","family":"Furukawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroaki","family":"Kobayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,6,23]]},"reference":[{"unstructured":"Arai, S., Miyazaki, K., Kobayashi, S.: Generating cooperative behavior by multi-agent reinforcement learning. In: Proceedings of the 6th European Workshop on Learning Robots, pp. 143\u2013157 (1997)","key":"15_CR1"},{"issue":"4","key":"15_CR2","first-page":"609","volume":"13","author":"S Arai","year":"1998","unstructured":"Arai, S., Miyazaki, K., Kobayashi, S.: Methodology in multi-agent reinforcement learning-approaches by Q-learning and profit sharing. Trans. Jpn. Soc. Artif. Intell. 13(4), 609\u2013618 (1998). (in Japanese)","journal-title":"Trans. Jpn. Soc. Artif. Intell."},{"issue":"6","key":"15_CR3","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1527\/tjsai.21.537","volume":"21","author":"S Arai","year":"2006","unstructured":"Arai, S., Tanaka, N.: Experimental analysis of reward design for continuing task in multiagent domains. Trans. Jpn. Soc. Artif. Intell. 21(6), 537\u2013546 (2006). RoboCup Soccer Keepaway - (in Japanese)","journal-title":"Trans. Jpn. Soc. Artif. Intell."},{"issue":"6","key":"15_CR4","doi-asserted-by":"crossref","first-page":"758","DOI":"10.20965\/jaciii.2012.p0758","volume":"16","author":"S Kuroda","year":"2013","unstructured":"Kuroda, S., Miyazaki, K., Kobayashi, H.: Introduction of fixed mode states into online reinforcement learning with penalty and reward and its application to waist trajectory generation of biped robot. J. Adv. Comput. Intell. Intell. Inform. 16(6), 758\u2013768 (2013)","journal-title":"J. Adv. Comput. Intell. Intell. Inform."},{"issue":"6","key":"15_CR5","doi-asserted-by":"crossref","first-page":"691","DOI":"10.20965\/jaciii.2009.p0691","volume":"13","author":"T Matsui","year":"2009","unstructured":"Matsui, T., Goto, T., Izumi, K.: Acquiring a government bond trading strategy using reinforcement learning. J. Adv. Comput. Intell. Intell. Inform. 13(6), 691\u2013696 (2009)","journal-title":"J. Adv. Comput. Intell. Intell. Inform."},{"doi-asserted-by":"crossref","unstructured":"Merrick, K., Maher, M.L.: Motivated reinforcement learning for adaptive characters in open-ended simulation games. In: Proceedings of the International Conference on Advanced in Computer Entertainment Technology, pp. 127\u2013134 (2007)","key":"15_CR6","DOI":"10.1145\/1255047.1255073"},{"unstructured":"Miyazaki, K., Yamamura, M., Kobayashi, S.: On the rationality of profit sharing in reinforcement learning. In: Proceedings of the 3rd International Conference on Fuzzy Logic, Neural Nets and Soft Computing, pp. 285\u2013288 (1994)","key":"15_CR7"},{"issue":"4","key":"15_CR8","first-page":"580","volume":"9","author":"K Miyazaki","year":"1994","unstructured":"Miyazaki, K., Yamamura, M., Kobayashi, H.: A theory of profit sharing in reinforcement learning. Trans. Jpn. Soc. Artif. Intell. 9(4), 580\u2013587 (1994). (in Japanese)","journal-title":"Trans. Jpn. Soc. Artif. Intell."},{"issue":"2","key":"15_CR9","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1007\/BF03037252","volume":"19","author":"K Miyazaki","year":"2001","unstructured":"Miyazaki, K., Kobayashi, S.: Rationality of reward sharing in multi-agent reinforcement learning. New Gener. Comput. 19(2), 157\u2013172 (2001)","journal-title":"New Gener. Comput."},{"issue":"6","key":"15_CR10","first-page":"1156","volume":"14","author":"K Miyazaki","year":"1999","unstructured":"Miyazaki, K., Arai, S., Kobayashi, S.: A theory of profit sharing in multi-agent reinforcement. Learning 14(6), 1156\u20131164 (1999). (in Japanese)","journal-title":"Learning"},{"issue":"5","key":"15_CR11","first-page":"285","volume":"18","author":"K Miyazaki","year":"2003","unstructured":"Miyazaki, K., Kobayashi, S.: An extension of profit sharing to partially observable Markov decision processes: proposition of PS-r* and its evaluation. J. Jpn. Soc. Artif. Intell. 18(5), 285\u2013296 (2003). (in Japanese)","journal-title":"J. Jpn. Soc. Artif. Intell."},{"doi-asserted-by":"crossref","unstructured":"Miyazaki, K., Kobayashi, S.: Reinforcement learning for penalty avoiding policy making. In: Proceedings of the 2000 IEEE International Conference on Systems, Man and Cybernetics, pp. 206\u2013211 (2000)","key":"15_CR12","DOI":"10.1109\/ICSMC.2000.884990"},{"issue":"2","key":"15_CR13","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1527\/tjsai.16.185","volume":"16","author":"K Miyazaki","year":"2001","unstructured":"Miyazaki, K., Tsuboi, S., Kobayashi, S.: Reinforcement learning for penalty avoiding rational policy making. Trans. Jpn. Soc. Artif. Intell. 16(2), 185\u2013192 (2001). (in Japanese)","journal-title":"Trans. Jpn. Soc. Artif. Intell."},{"issue":"6","key":"15_CR14","doi-asserted-by":"crossref","first-page":"624","DOI":"10.20965\/jaciii.2009.p0624","volume":"13","author":"K Miyazaki","year":"2009","unstructured":"Miyazaki, K., Kobayashi, S.: Exploitation-oriented learning PS-r#. J. Adv. Comput. Intell. Intell. Inform. 13(6), 624\u2013630 (2009)","journal-title":"J. Adv. Comput. Intell. Intell. Inform."},{"issue":"7","key":"15_CR15","doi-asserted-by":"crossref","first-page":"1683","DOI":"10.4304\/jcp.8.7.1683-1690","volume":"8","author":"K Miyazaki","year":"2013","unstructured":"Miyazaki, K.: Proposal of an exploitation-oriented learning method on multiple rewards and penalties environments and the design guideline. J. Comput. 8(7), 1683\u20131690 (2013)","journal-title":"J. Comput."},{"key":"15_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1007\/978-3-642-29946-9_32","volume-title":"Recent Advances in Reinforcement Learning","author":"K Miyazaki","year":"2012","unstructured":"Miyazaki, K., Ida, M.: Proposal and evaluation of the active course classification support system with exploitation-oriented learning. In: Sanner, S., Hutter, M. (eds.) EWRL 2011. LNCS, vol. 7188, pp. 333\u2013344. Springer, Heidelberg (2012). doi:\n10.1007\/978-3-642-29946-9_32"},{"unstructured":"Miyazaki, K., Muraoka, H., Kobayashi, H.: Proposal of a propagation algorithm of the expected failure probability and the effectiveness on multi-agent environments. In: SICE Annual Conference 2013, pp. 1067\u20131072 (2013)","key":"15_CR17"},{"unstructured":"Miyazaki, K.: Exploitation-oriented Learning XoL with deep learning - comparison with a deep Q-network. The Papers of Technical Meeting on \u201cSystems\u201d, IEE Japan, pp. 7\u201312 (2016). (in Japanese)","key":"15_CR18"},{"unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing atari with deep reinforcement learning. In: NIPS Deep Learning Workshop 2013 (2013)","key":"15_CR19"},{"issue":"3","key":"15_CR20","first-page":"273","volume":"136","author":"H Muraoka","year":"2016","unstructured":"Muraoka, H., Miyazaki, K., Kobayashi, H.: Proposal of a propagation algorithm of the expected failure probability and the effectiveness on multi-agent environments. Trans. Inst. Electr. Eng. Jpn. C 136(3), 273\u2013281 (2016). (in Japanese)","journal-title":"Trans. Inst. Electr. Eng. Jpn. C"},{"unstructured":"Randl\n            $$\\phi $$\n          v, J., Alstr\n            $$\\phi $$\n          m, P.: Learning to drive a bicycle using reinforcement learning and shaping. In: Proceedings of the 15th International Conference on Machine Learning, pp. 463\u2013471 (1998)","key":"15_CR21"},{"key":"15_CR22","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C.J., Guez, A., Sifre, L., Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., Dieleman, S., Grewe, D., Nham, J., Kalchbrenner, N., Sutskever, I., Lillicrap, T., Leach, M., Kavukcuoglu, K., Graepel, T., Hassabis, D.: Mastering the game of Go with deep neural networks and tree search. Nature 529, 484\u2013489 (2016)","journal-title":"Nature"},{"issue":"2","key":"15_CR23","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1109\/TAMD.2010.2051031","volume":"2","author":"S Singh","year":"2010","unstructured":"Singh, S., Lewis, R.L., Barto, A.G., Sorg, J.: Intrinsically motivated reinforcement learning: an evolutionary perspective. IEEE Trans. Auton. Ment. Dev. 2(2), 70\u201382 (2010)","journal-title":"IEEE Trans. Auton. Ment. Dev."},{"issue":"3","key":"15_CR24","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1177\/105971230501300301","volume":"13","author":"P Stone","year":"2005","unstructured":"Stone, P., Sutton, R.S., Kuhlamann, G.: Reinforcement learning toward robocup soccer keepaway. Adapt. Behav. 13(3), 165\u2013188 (2005)","journal-title":"Adapt. Behav."},{"key":"15_CR25","volume-title":"Reinforcement Learning: An Introduction, A Bradford Book","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, A Bradford Book. MIT Press, Cambridge (1998)"},{"issue":"6","key":"15_CR26","doi-asserted-by":"crossref","first-page":"678","DOI":"10.20965\/jaciii.2009.p0675","volume":"13","author":"T Watanabe","year":"2009","unstructured":"Watanabe, T., Miyazaki, K., Kobayashi, H.: A new improved penalty avoiding rational policy making algorithm for keepaway with continuous state spaces. J. Adv. Comput. Intell. Intell. Inform. 13(6), 678\u2013682 (2009)","journal-title":"J. Adv. Comput. Intell. Intell. Inform."},{"issue":"2","key":"15_CR27","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1007\/s10015-004-0340-6","volume":"9","author":"J Yoshimoto","year":"2005","unstructured":"Yoshimoto, J., Nishimura, M., Tokita, Y., Ishii, S.: Acrobot control by learning the switching of multiple controllers. J. Artif. Life Robot. 9(2), 67\u201371 (2005)","journal-title":"J. Artif. Life Robot."}],"container-title":["Lecture Notes in Computer Science","Multi-Agent Systems and Agreement Technologies"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-59294-7_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,22]],"date-time":"2017-06-22T10:25:57Z","timestamp":1498127157000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-59294-7_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319592930","9783319592947"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-59294-7_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}