{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T09:09:24Z","timestamp":1742980164595,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030638320"},{"type":"electronic","value":"9783030638337"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/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":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-63833-7_55","type":"book-chapter","created":{"date-parts":[[2020,11,19]],"date-time":"2020-11-19T06:03:35Z","timestamp":1605765815000},"page":"651-662","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Stable Deep Reinforcement Learning Method by Predicting Uncertainty in Rewards as a Subtask"],"prefix":"10.1007","author":[{"given":"Kanata","family":"Suzuki","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsuya","family":"Ogata","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,20]]},"reference":[{"key":"55_CR1","unstructured":"Anschel, O., Baram, N., Shimkin, N.: Averaged-DQN: variance reduction and stabilization for deep reinforcement learning. In: The International Conference on Machine Learning (2017)"},{"key":"55_CR2","unstructured":"Ba, J., Kingma, D.P.: Adam: a method for stochastic optimization. In: Proceedings of International Conference on Learning Representations (2015)"},{"key":"55_CR3","unstructured":"Brockman, G., et al.: OpenAI Gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"55_CR4","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12, 2121\u20132159 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"55_CR5","doi-asserted-by":"crossref","unstructured":"Everitt, T., Krakovna, V., Orseau, L., Hutter, M., Legg, S.: Reinforcement learning with a corrupted reward channel. In: 26th International Joint Conference on Artificial Intelligence, IJCAI-17, pp. 4705\u20134713 (2017)","DOI":"10.24963\/ijcai.2017\/656"},{"key":"55_CR6","doi-asserted-by":"crossref","unstructured":"Fukui, H., Hirakawa, T., Yamashita, T., Fujiyoshi, H.: Attention branch network: learning of attention mechanism for visual explanation. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01096"},{"key":"55_CR7","doi-asserted-by":"crossref","unstructured":"van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double Q-learning. In: Proceedings of the 13th AAAI Conference on Artificial Intelligence (2016)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"55_CR8","unstructured":"Jang, E., Devin, C., Vanhoucke, V., Levine, S.: Grasp2Vec: learning object representations from self-supervised grasping. In: Conference on Robot Learning (CoRL) (2018)"},{"key":"55_CR9","unstructured":"Johnson, R., Zhang, T.: Accelerating stochastic gradient descent using predictive variance reduction. In: Advances in Neural Information Processing Systems, pp. 315\u2013323 (2013)"},{"key":"55_CR10","doi-asserted-by":"crossref","unstructured":"Kase, K., Suzuki, K., Yang, P.C., Mori, H., Ogata, T.: Put-in-box task generated from multiple discrete tasks by a humanoid robot using deep learning. In: Proceedings of the IEEE International Conference on Robots and Automation (2018)","DOI":"10.1109\/ICRA.2018.8460623"},{"issue":"4\u20135","key":"55_CR11","first-page":"421","volume":"37","author":"S Levine","year":"2017","unstructured":"Levine, S., Pastor, P., Krizhevsky, A., Quillen, D.: Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection. Int. J. Robot. Res. 37(4\u20135), 421\u2013436 (2017)","journal-title":"Int. J. Robot. Res."},{"issue":"39","key":"55_CR12","first-page":"1","volume":"17","author":"S Levine","year":"2016","unstructured":"Levine, S., Finn, C., Darrell, T., Abbeel, P.: End-to-end training of deep visuomotor policies. J. Mach. Learn. Res. 17(39), 1\u201340 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"55_CR13","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518, 529\u2013533 (2015)","journal-title":"Nature"},{"key":"55_CR14","unstructured":"Mnih, V.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning (ICML) (2016)"},{"key":"55_CR15","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1109\/TAMD.2013.2258019","volume":"5","author":"S Murata","year":"2013","unstructured":"Murata, S., Namikawa, J., Arie, H., Sugano, S., Tani, J.: Learning to reproduce fluctuating time series by inferring their time-dependent stochastic properties: application in robot learning via tutoring. IEEE Trans. Auton. Ment. Dev. 5, 298\u2013310 (2013)","journal-title":"IEEE Trans. Auton. Ment. Dev."},{"key":"55_CR16","unstructured":"Romoff, J., Henderson, P., Pich\u00e9, A., F-Lavet, V., Pineau, J.: Reward Estimation for Variance Reduction in Deep Reinforcement Learning. arXiv preprint arXiv:1805.03359 (2018)"},{"key":"55_CR17","first-page":"2663","volume":"25","author":"NL Roux","year":"2012","unstructured":"Roux, N.L., Schmidt, M., Bach, F.: A stochastic gradient method with an exponential convergence rate for finite training sets. Adv. Neural Inf. Process. Syst. 25, 2663\u20132671 (2012)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"55_CR18","first-page":"567","volume":"14","author":"SS Shwars","year":"2013","unstructured":"Shwars, S.S., Zhang, T.: Stochastic dual coordinate ascent methods for regularized loss minimization. J. Mach. Learn. Res. 14, 567\u2013599 (2013)","journal-title":"J. Mach. Learn. Res."},{"key":"55_CR19","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of Go with deep neural networks and tree search. Nature 529, 484\u2013489 (2016)","journal-title":"Nature"},{"issue":"4","key":"55_CR20","doi-asserted-by":"publisher","first-page":"3481","DOI":"10.1109\/LRA.2018.2853651","volume":"3","author":"K Suzuki","year":"2018","unstructured":"Suzuki, K., Mori, H., Ogata, T.: Motion switching with sensory and instruction signals by designing dynamical systems using deep neural network. IEEE Robot. Autom. Lett. 3(4), 3481\u20133488 (2018)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"55_CR21","doi-asserted-by":"crossref","unstructured":"Suzuki, K., Yokota, Y., Kanazawa, Y., Takebayashi, T.: Online self-supervised learning for object picking: detecting optimum grasping position using a metric learning approach. In: Proceedings of International Symposium on System Integrations (2020)","DOI":"10.1109\/SII46433.2020.9025845"},{"issue":"2","key":"55_CR22","first-page":"26","volume":"4","author":"T Tieleman","year":"2012","unstructured":"Tieleman, T., Hinton, G.: Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA: Neural Netw. Mach. Learn. 4(2), 26\u201330 (2012)","journal-title":"COURSERA: Neural Netw. Mach. Learn."},{"key":"55_CR23","doi-asserted-by":"crossref","unstructured":"Wang, F., et al.: Residual attention network for image classification. In: Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.683"},{"key":"55_CR24","unstructured":"Zhao, W.Y., Guan, X.Y., Liu, Y., Zhao, X., Peng, J.: Stochastic Variance Reduction for Deep Q-learning. arXiv preprint arXiv:1905.08152 (2019)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-63833-7_55","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T11:04:55Z","timestamp":1710327895000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-63833-7_55"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030638320","9783030638337"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-63833-7_55","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":"20 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bangkok","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","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":"18 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.apnns.org\/ICONIP2020","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"618","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":"187","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":"189","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":"30% - 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":"3.18","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":"3.68","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to COVID-19 pandemic the conference was held virtually.","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)"}}]}}