{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T04:50:18Z","timestamp":1743137418397,"version":"3.40.3"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030166915"},{"type":"electronic","value":"9783030166922"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-16692-2_10","type":"book-chapter","created":{"date-parts":[[2019,4,9]],"date-time":"2019-04-09T23:44:24Z","timestamp":1554853464000},"page":"141-155","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Efficient Online Hyperparameter Adaptation for Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Yinda","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,3,30]]},"reference":[{"key":"10_CR1","unstructured":"Li, Y.: Deep reinforcement learning: An overview. arXiv preprint arXiv:1701.07274 (2017)"},{"key":"10_CR2","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G., Bach, F., et al.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"issue":"7553","key":"10_CR3","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436 (2015)","journal-title":"Nature"},{"issue":"7587","key":"10_CR4","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(7587), 484 (2016)","journal-title":"Nature"},{"issue":"7676","key":"10_CR5","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354 (2017)","journal-title":"Nature"},{"issue":"7540","key":"10_CR6","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(7540), 529 (2015)","journal-title":"Nature"},{"key":"10_CR7","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"10_CR8","unstructured":"Justesen, N., Bontrager, P., Togelius, J., Risi, S.: Deep learning for video game playing. arXiv preprint arXiv:1708.07902 (2017)"},{"issue":"1","key":"10_CR9","first-page":"1334","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(1), 1334\u20131373 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"10_CR10","unstructured":"Mirowski, P., et al.: Learning to navigate in complex environments. arXiv preprint arXiv:1611.03673 (2016)"},{"key":"10_CR11","unstructured":"Yoo, S., Yun, K., Choi, J.Y.: Action-decision networks for visual tracking with deep reinforcement learning. In: CVPR, pp. 2711\u20132720 (2017)"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Ren, Z., Wang, X., Zhang, N., Lv, X., Li, L.J.: Deep reinforcement learning-based image captioning with embedding reward. arXiv preprint arXiv:1704.03899 (2017)","DOI":"10.1109\/CVPR.2017.128"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wang, N., Zhang, L.: Multi-shot pedestrian re-identification via sequential decision making. arXiv preprint arXiv:1712.07257 (2017)","DOI":"10.1109\/CVPR.2018.00709"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Henderson, P., Islam, R., Bachman, P., Pineau, J., Precup, D., Meger, D.: Deep reinforcement learning that matters. arXiv preprint arXiv:1709.06560 (2017)","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"10_CR15","unstructured":"Islam, R., Henderson, P., Gomrokchi, M., Precup, D.: Reproducibility of benchmarked deep reinforcement learning tasks for continuous control. arXiv preprint arXiv:1708.04133 (2017)"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Elfwing, S., Uchibe, E., Doya, K.: Online meta-learning by parallel algorithm competition. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 426\u2013433. ACM (2018)","DOI":"10.1145\/3205455.3205486"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Melo, F.S., Meyn, S.P., Ribeiro, M.I.: An analysis of reinforcement learning with function approximation. In: Proceedings of the 25th international conference on Machine learning, pp. 664\u2013671. ACM (2008)","DOI":"10.1145\/1390156.1390240"},{"key":"10_CR18","unstructured":"Fran\u00e7ois-Lavet, V., Fonteneau, R., Ernst, D.: How to discount deep reinforcement learning: Towards new dynamic strategies. arXiv preprint arXiv:1512.02011 (2015)"},{"key":"10_CR19","unstructured":"Downey, C., Sanner, S., et al.: Temporal difference bayesian model averaging: A bayesian perspective on adapting lambda. In: ICML, pp. 311\u2013318. Citeseer (2010)"},{"issue":"4\u20136","key":"10_CR20","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1016\/S0893-6080(02)00056-4","volume":"15","author":"S Ishii","year":"2002","unstructured":"Ishii, S., Yoshida, W., Yoshimoto, J.: Control of exploitation-exploration meta-parameter in reinforcement learning. Neural Netw. 15(4\u20136), 665\u2013687 (2002)","journal-title":"Neural Netw."},{"key":"10_CR21","unstructured":"Mann, T.A., Penedones, H., Mannor, S., Hester, T.: Adaptive lambda least-squares temporal difference learning. arXiv preprint arXiv:1612.09465 (2016)"},{"key":"10_CR22","unstructured":"Jaderberg, M., et al.: Population based training of neural networks. arXiv preprint arXiv:1711.09846 (2017)"},{"key":"10_CR23","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937 (2016)"},{"key":"10_CR24","first-page":"2094","volume":"16","author":"H Hasselt Van","year":"2016","unstructured":"Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. AAAI 16, 2094\u20132100 (2016)","journal-title":"AAAI"},{"key":"10_CR25","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. arXiv preprint arXiv:1511.05952 (2015)"},{"key":"10_CR26","unstructured":"Wang, Z., Schaul, T., Hessel, M., Van Hasselt, H., Lanctot, M., De Freitas, N.: Dueling network architectures for deep reinforcement learning. arXiv preprint arXiv:1511.06581 (2015)"},{"key":"10_CR27","unstructured":"Anschel, O., Baram, N., Shimkin, N.: Averaged-dqn: Variance reduction and stabilization for deep reinforcement learning. arXiv preprint arXiv:1611.01929 (2016)"},{"key":"10_CR28","unstructured":"Fortunato, M., et al.: Noisy networks for exploration. arXiv preprint arXiv:1706.10295 (2017)"},{"key":"10_CR29","unstructured":"Hessel, M., et al.: Rainbow: Combining improvements in deep reinforcement learning. arXiv preprint arXiv:1710.02298 (2017)"},{"key":"10_CR30","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"10_CR31","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889\u20131897 (2015)"},{"key":"10_CR32","unstructured":"Wu, Y., Mansimov, E., Grosse, R.B., Liao, S., Ba, J.: Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation. In: Advances in Neural Information Processing Systems, pp. 5285\u20135294 (2017)"},{"key":"10_CR33","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"10_CR34","first-page":"281","volume":"13","author":"J Bergstra","year":"2012","unstructured":"Bergstra, J., Bengio, Y.: Random search for hyper-parameter optimization. J. Mach. Learn. Res. 13, 281\u2013305 (2012)","journal-title":"J. Mach. Learn. Res."},{"key":"10_CR35","unstructured":"Snoek, J., Larochelle, H., Adams, R.P.: Practical bayesian optimization of machine learning algorithms. In: Advances in neural information processing systems, pp. 2951\u20132959 (2012)"},{"key":"10_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1007\/978-3-642-25566-3_40","volume-title":"Learning and Intelligent Optimization","author":"F Hutter","year":"2011","unstructured":"Hutter, F., Hoos, H.H., Leyton-Brown, K.: Sequential model-based optimization for general algorithm configuration. In: Coello, C.A.C. (ed.) LION 2011. LNCS, vol. 6683, pp. 507\u2013523. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-25566-3_40"},{"key":"10_CR37","unstructured":"Bergstra, J.S., Bardenet, R., Bengio, Y., K\u00e9gl, B.: Algorithms for hyper-parameter optimization. In: Advances in Neural Information Processing Systems, pp. 2546\u20132554 (2011)"},{"key":"10_CR38","unstructured":"Bergstra, J., Yamins, D., Cox, D.: Making a science of model search: hyperparameter optimization in hundreds of dimensions for vision architectures. In: International Conference on Machine Learning, pp. 115\u2013123 (2013)"},{"issue":"2","key":"10_CR39","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\u201331 (2012)","journal-title":"COURSERA Neural Netw. Mach. Learn."}],"container-title":["Lecture Notes in Computer Science","Applications of Evolutionary Computation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-16692-2_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,15]],"date-time":"2022-09-15T16:28:11Z","timestamp":1663259291000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-16692-2_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030166915","9783030166922"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-16692-2_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"30 March 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EvoApplications","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on the Applications of Evolutionary Computation (Part of EvoStar)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Leipzig","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 April 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 April 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"evoapplications2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.evostar.org\/2019\/cfp_evoapps.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"MyReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"66","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"44","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"24","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"67% - 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"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}