{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T20:03:45Z","timestamp":1743019425467,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030581145"},{"type":"electronic","value":"9783030581152"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/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":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58115-2_36","type":"book-chapter","created":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T22:02:51Z","timestamp":1598997771000},"page":"515-527","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["ClipUp: A Simple and Powerful Optimizer for Distribution-Based Policy Evolution"],"prefix":"10.1007","author":[{"given":"Nihat Engin","family":"Toklu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8165-748X","authenticated-orcid":false,"given":"Pawe\u0142","family":"Liskowski","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4032-4267","authenticated-orcid":false,"given":"Rupesh Kumar","family":"Srivastava","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,2]]},"reference":[{"key":"36_CR1","unstructured":"Brockman, G., et al.: OpenAI Gym. arXiv preprint \narXiv:1606.01540\n\n (2016)"},{"key":"36_CR2","unstructured":"Choi, D., Shallue, C.J., Nado, Z., Lee, J., Maddison, C.J., Dahl, G.E.: On empirical comparisons of optimizers for deep learning. arXiv preprint \narXiv:1910.05446\n\n (2019)"},{"key":"36_CR3","unstructured":"Coumans, E.: Pybullet repository - issues. \nhttps:\/\/github.com\/bulletphysics\/bullet3\/issues\/1718#issuecomment-393198883\n\n (2018)"},{"key":"36_CR4","unstructured":"Coumans, E., Bai, Y.: Pybullet, a python module for physics simulation for games, robotics and machine learning. \nhttp:\/\/pybullet.org\n\n (2016-2019)"},{"key":"36_CR5","doi-asserted-by":"publisher","unstructured":"Erez, T., Tassa, Y., Todorov, E.: Infinite-horizon model predictive control for periodic tasks with contacts. In: Durrant-Whyte, H.F., Roy, N., Abbeel, P. (eds.) Robotics: Science and Systems VII, University of Southern California, Los Angeles, CA, USA, 27\u201330 June 2011 (2011). \nhttps:\/\/doi.org\/10.15607\/RSS.2011.VII.010\n\n. \nhttp:\/\/www.roboticsproceedings.org\/rss07\/p10.html","DOI":"10.15607\/RSS.2011.VII.010"},{"key":"36_CR6","unstructured":"Freeman, D., Ha, D., Metz, L.: Learning to predict without looking ahead: World models without forward prediction. In: Advances in Neural Information Processing Systems, pp. 5380\u20135391 (2019)"},{"key":"36_CR7","unstructured":"Ha, D.: A visual guide to evolution strategies. blog.otoro.net (2017). \nhttp:\/\/blog.otoro.net\/2017\/10\/29\/visual-evolution-strategies\/"},{"key":"36_CR8","doi-asserted-by":"publisher","unstructured":"Ha, D.: Reinforcement learning for improving agent design. Artificial Life 25(4), 352\u2013365 (2019). \nhttps:\/\/doi.org\/10.1162\/artl_a_00301\n\n. pMID: 31697584","DOI":"10.1162\/artl_a_00301"},{"key":"36_CR9","first-page":"650","volume":"97","author":"N Hansen","year":"1997","unstructured":"Hansen, N., Ostermeier, A.: Convergence properties of evolution strategies with the derandomized covariance matrix adaptation: The ($$\\mu $$\/$$\\mu _{I}$$,$$\\lambda $$)-cma-es. Eufit 97, 650\u2013654 (1997)","journal-title":"Eufit"},{"issue":"2","key":"36_CR10","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1162\/106365601750190398","volume":"9","author":"N Hansen","year":"2001","unstructured":"Hansen, N., Ostermeier, A.: Completely derandomized self-adaptation in evolution strategies. Evol. Comput. 9(2), 159\u2013195 (2001)","journal-title":"Evol. Comput."},{"key":"36_CR11","unstructured":"Hochreiter, S.: Untersuchungen zu dynamischen neuronalen Netzen. Masters thesis, Technische Universit\u00e4t M\u00fcnchen, M\u00fcnchen (1991)"},{"key":"36_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of 3rd International Conference on Learning Representations (2015)"},{"key":"36_CR13","unstructured":"Klimov, O., Schulman, J.: Roboschool. OpenAI blog (2017). \nhttps:\/\/openai.com\/blog\/roboschool\/"},{"key":"36_CR14","unstructured":"Mania, H., Guy, A., Recht, B.: Simple random search of static linear policies is competitive for reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 1800\u20131809 (2018)"},{"key":"36_CR15","unstructured":"Pascanu, R., Mikolov, T., Bengio, Y.: On the difficulty of training recurrent neural networks. In: International conference on machine learning, pp. 1310\u20131318 (2013)"},{"issue":"5","key":"36_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0041-5553(64)90137-5","volume":"4","author":"BT Polyak","year":"1964","unstructured":"Polyak, B.T.: Some methods of speeding up the convergence of iteration methods. USSR Comput. Math. Math. Phys. 4(5), 1\u201317 (1964)","journal-title":"USSR Comput. Math. Math. Phys."},{"key":"36_CR17","unstructured":"Rajeswaran, A., Lowrey, K., Todorov, E.V., Kakade, S.M.: Towards generalization and simplicity in continuous control. In: Advances in Neural Information Processing Systems, pp. 6550\u20136561 (2017)"},{"key":"36_CR18","unstructured":"Salimans, T., Ho, J., Chen, X., Sidor, S., Sutskever, I.: Evolution strategies as a scalable alternative to reinforcement learning. arXiv preprint \narXiv:1703.03864\n\n (2017)"},{"issue":"2","key":"36_CR19","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1109\/4235.728207","volume":"2","author":"R Salomon","year":"1998","unstructured":"Salomon, R.: Evolutionary algorithms and gradient search: similarities and differences. IEEE Trans. Evol. Comput. 2(2), 45\u201355 (1998)","journal-title":"IEEE Trans. Evol. Comput."},{"key":"36_CR20","unstructured":"Salomon, R.: Inverse mutations: making the evolutionary-gradient-search procedure noise robust. In: Proceedings of the IASTED International Conference on Artificial Intelligence and Applications, pp. 322\u2013327 (2005)"},{"issue":"4","key":"36_CR21","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1016\/j.neunet.2009.12.004","volume":"23","author":"F Sehnke","year":"2010","unstructured":"Sehnke, F., Osendorfer, C., R\u00fcckstie\u00df, T., Graves, A., Peters, J., Schmidhuber, J.: Parameter-exploring policy gradients. Neural Netw. 23(4), 551\u2013559 (2010)","journal-title":"Neural Netw."},{"key":"36_CR22","doi-asserted-by":"crossref","unstructured":"Tassa, Y., Erez, T., Todorov, E.: Synthesis and stabilization of complex behaviors through online trajectory optimization. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 4906\u20134913. IEEE (2012)","DOI":"10.1109\/IROS.2012.6386025"},{"key":"36_CR23","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: MuJoCo: A physics engine for model-based control. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5026\u20135033. IEEE (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"issue":"1","key":"36_CR24","first-page":"949","volume":"15","author":"D Wierstra","year":"2014","unstructured":"Wierstra, D., Schaul, T., Glasmachers, T., Sun, Y., Peters, J., Schmidhuber, J.: Natural evolution strategies. J. Mach. Learn. Res. 15(1), 949\u2013980 (2014)","journal-title":"J. Mach. Learn. Res."},{"issue":"3\u20134","key":"36_CR25","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3\u20134), 229\u2013256 (1992). \nhttps:\/\/doi.org\/10.1007\/BF00992696","journal-title":"Mach. Learn."},{"key":"36_CR26","unstructured":"Zhang, J., He, T., Sra, S., Jadbabaie, A.: Why gradient clipping accelerates training: a theoretical justification for adaptivity. In: International Conference on Learning Representations (2020)"}],"container-title":["Lecture Notes in Computer Science","Parallel Problem Solving from Nature \u2013 PPSN XVI"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58115-2_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T22:08:16Z","timestamp":1598998096000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-58115-2_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030581145","9783030581152"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58115-2_36","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":"2 September 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PPSN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Parallel Problem Solving from Nature","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Leiden","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","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":"5 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ppsn2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ppsn2020.liacs.leidenuniv.nl\/","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":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"268","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":"99","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":"37% - 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":"2.2","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)"}}]}}