{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T18:19:59Z","timestamp":1772302799114,"version":"3.50.1"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031216886","type":"print"},{"value":"9783031216893","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-21689-3_30","type":"book-chapter","created":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T10:03:56Z","timestamp":1668765836000},"page":"417-433","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Learning Global Optimization by\u00a0Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Mo\u00e9sio Wenceslau","family":"da Silva Filho","sequence":"first","affiliation":[]},{"given":"Gabriel A.","family":"Barbosa","sequence":"additional","affiliation":[]},{"given":"P\u00e9ricles B. C.","family":"Miranda","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,19]]},"reference":[{"key":"30_CR1","first-page":"1","volume":"29","author":"M Andrychowicz","year":"2016","unstructured":"Andrychowicz, M., et al.: Learning to learn by gradient descent by gradient descent. Adv. Neural Inf. Process. Syst. 29, 1\u20139 (2016)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"6","key":"30_CR2","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MSP.2017.2743240","volume":"34","author":"K Arulkumaran","year":"2017","unstructured":"Arulkumaran, K., Deisenroth, M.P., Brundage, M., Bharath, A.A.: Deep reinforcement learning: a brief survey. IEEE Signal Process. Mag. 34(6), 26\u201338 (2017)","journal-title":"IEEE Signal Process. Mag."},{"key":"30_CR3","unstructured":"Bello, I., Zoph, B., Vasudevan, V., Le, Q.V.: Neural optimizer search with reinforcement learning. In: Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 70, pp. 459\u2013468. PMLR (2017)"},{"key":"30_CR4","first-page":"1","volume":"32","author":"Y Cao","year":"2019","unstructured":"Cao, Y., Chen, T., Wang, Z., Shen, Y.: Learning to optimize in swarms. Adv. Neural Inf. Process. Syst. 32, 1\u201311 (2019)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"30_CR5","first-page":"7332","volume":"33","author":"T Chen","year":"2020","unstructured":"Chen, T., et al.: Training stronger baselines for learning to optimize. Adv. Neural Inf. Process. Syst. 33, 7332\u20137343 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"30_CR6","unstructured":"Chen, Y., et al.: Learning to learn without gradient descent by gradient descent. In: Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 70, pp. 748\u2013756. PMLR (2017)"},{"key":"30_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1007\/978-3-030-05348-2_24","volume-title":"Learning and Intelligent Optimization","author":"L Faury","year":"2019","unstructured":"Faury, L., Vasile, F.: Rover descent: learning to optimize by learning to navigate on prototypical loss surfaces. In: Battiti, R., Brunato, M., Kotsireas, I., Pardalos, P.M. (eds.) LION 12 2018. LNCS, vol. 11353, pp. 271\u2013287. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-05348-2_24"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Filho, M.S., Barbosa, G., Miranda, P., Nascimento, A., Mello, R.: Zeroth order policy search methods for global optimization problems: an experimental study. In: Anais do XVIII Encontro Nacional de Intelig\u00eancia Artificial e Computacional, pp. 209\u2013220. SBC (2021)","DOI":"10.5753\/eniac.2021.18254"},{"key":"30_CR9","unstructured":"Fujimoto, S., van Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 80, pp. 1587\u20131596. PMLR (2018)"},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"Hessel, M., Soyer, H., Espeholt, L., Czarnecki, W., Schmitt, S., van Hasselt, H.: Multi-task deep reinforcement learning with popart. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 01, pp. 3796\u20133803 (2019)","DOI":"10.1609\/aaai.v33i01.33013796"},{"key":"30_CR11","unstructured":"Igl, M., Zintgraf, L., Le, T.A., Wood, F., Whiteson, S.: Deep variational reinforcement learning for POMDPs. In: Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 80, pp. 2117\u20132126. PMLR (2018)"},{"issue":"2","key":"30_CR12","first-page":"150","volume":"4","author":"M Jamil","year":"2013","unstructured":"Jamil, M., Yang, X.S.: A literature survey of benchmark functions for global optimisation problems. Int. J. Math. Model. Numer. Optim. 4(2), 150\u2013194 (2013)","journal-title":"Int. J. Math. Model. Numer. Optim."},{"key":"30_CR13","unstructured":"Li, K., Malik, J.: Learning to optimize. In: 5th International Conference on Learning Representations (2017)"},{"key":"30_CR14","unstructured":"Li, K., Malik, J.: Learning to optimize neural nets. CoRR (2017)"},{"key":"30_CR15","unstructured":"Lv, K., Jiang, S., Li, J.: Learning gradient descent: better generalization and longer horizons. In: Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 70, pp. 2247\u20132255. PMLR (2017)"},{"key":"30_CR16","unstructured":"Metz, L., Maheswaranathan, N., Nixon, J., Freeman, D., Sohl-Dickstein, J.: Understanding and correcting pathologies in the training of learned optimizers. In: Proceedings of the 36th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 97, pp. 4556\u20134565. PMLR (2019)"},{"key":"30_CR17","unstructured":"Ni, T., Eysenbach, B., Salakhutdinov, R.: Recurrent model-free RL is a strong baseline for many pomdps. CoRR (2021)"},{"key":"30_CR18","doi-asserted-by":"crossref","unstructured":"Nobile, M.S., Cazzaniga, P., Ashlock, D.A.: Dilation functions in global optimization. In: 2019 IEEE Congress on Evolutionary Computation (CEC), pp. 2300\u20132307 (2019)","DOI":"10.1109\/CEC.2019.8790247"},{"key":"30_CR19","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1007\/978-3-030-46147-8_22","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"V TV","year":"2020","unstructured":"TV, V., Malhotra, P., Narwariya, J., Vig, L., Shroff, G.: Meta-learning for black-box optimization. In: Brefeld, U., Fromont, E., Hotho, A., Knobbe, A., Maathuis, M., Robardet, C. (eds.) ECML PKDD 2019. LNCS (LNAI), vol. 11907, pp. 366\u2013381. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-46147-8_22"},{"key":"30_CR20","doi-asserted-by":"crossref","unstructured":"Webber, J.B.W.: A bi-symmetric log transformation for wide-range data. Meas. Sci. Technol. 24(2), 027001 (2012)","DOI":"10.1088\/0957-0233\/24\/2\/027001"},{"key":"30_CR21","unstructured":"Wichrowska, O., et al.: Learned optimizers that scale and generalize. In: Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 70, pp. 3751\u20133760. PMLR (2017)"},{"issue":"3","key":"30_CR22","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1080\/09540099108946587","volume":"3","author":"RJ Williams","year":"1991","unstructured":"Williams, R.J., Peng, J.: Function optimization using connectionist reinforcement learning algorithms. Connect. Sci. 3(3), 241\u2013268 (1991)","journal-title":"Connect. Sci."},{"key":"30_CR23","unstructured":"Yu, T., et al.: Meta-world: a benchmark and evaluation for multi-task and meta reinforcement learning. In: Proceedings of the Conference on Robot Learning. Proceedings of Machine Learning Research, vol. 100, pp. 1094\u20131100. PMLR (2020)"},{"key":"30_CR24","unstructured":"Zhang, H., Sun, J., Xu, Z.: Learning to be global optimizer. CoRR (2020)"}],"container-title":["Lecture Notes in Computer Science","Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-21689-3_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T01:32:07Z","timestamp":1728437527000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-21689-3_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031216886","9783031216893"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-21689-3_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"19 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BRACIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazilian Conference on Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Campinas","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazil","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bracis2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www2.sbc.org.br\/bracis2022\/","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 (provided by the conference organizers)"}},{"value":"JEMS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"225","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":"89","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":"0","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":"40% - 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","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":"4","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)"}}]}}