{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T09:43:46Z","timestamp":1775123026126,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,7,2]],"date-time":"2018-07-02T00:00:00Z","timestamp":1530489600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,7,2]]},"DOI":"10.1145\/3205455.3205486","type":"proceedings-article","created":{"date-parts":[[2018,7,3]],"date-time":"2018-07-03T12:30:37Z","timestamp":1530621037000},"page":"426-433","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Online meta-learning by parallel algorithm competition"],"prefix":"10.1145","author":[{"given":"Stefan","family":"Elfwing","sequence":"first","affiliation":[{"name":"ATR Computational Neuroscience Laboratories, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eiji","family":"Uchibe","sequence":"additional","affiliation":[{"name":"ATR Computational Neuroscience Laboratories, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenji","family":"Doya","sequence":"additional","affiliation":[{"name":"Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,7,2]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/42512.42515"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/2566972.2566979"},{"key":"e_1_3_2_1_3_1","volume-title":"Technical Report LIDS-P-2349.MIT.","author":"Bertsekas D. P.","year":"1996","unstructured":"D. P. Bertsekas and S. Ioffe. 1996. Temporal differences based policy iteration and applications in neuro-dynamic programming. Technical Report LIDS-P-2349.MIT."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.2307\/3619195"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104363"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1177\/1059712308092835"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1177\/1059712310397633"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2003.1250664"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"S. Fau\u00dfer and F. Schwenker. 2013. Neural Network Ensembles in Reinforcement Learning. Neural Processing Letters (2013) 1--15.","DOI":"10.1007\/s11063-013-9334-5"},{"key":"e_1_3_2_1_11_1","volume-title":"How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategies. arXiv:1512.02011 {cs.LG}","author":"Fran\u00e7ois-Lavet Vincent","year":"2015","unstructured":"Vincent Fran\u00e7ois-Lavet, Rapha\u00ebl Fonteneau, and Damien Ernst. 2015. How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategies. arXiv:1512.02011 {cs.LG} (2015)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999792.2999808"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25566-3_40"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(02)00056-4"},{"key":"e_1_3_2_1_16_1","volume-title":"Population Based Training of Neural Networks. arXiv:1711.09846 {cs.LG}","author":"Jaderberg Max","year":"2017","unstructured":"Max Jaderberg, Valentin Dalibard, Simon Osindero, Wojciech M. Czarnecki, Jeff Donahue, Ali Razavi, Oriol Vinyals, Tim Green, Iain Dunning, Karen Simonyana, Chrisantha Fernando, and Koray Kavukcuoglu. 2017. Population Based Training of Neural Networks. arXiv:1711.09846 {cs.LG} (2017)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-10677-4_60"},{"key":"e_1_3_2_1_18_1","unstructured":"J. B. Lamarck. 1809. Philosophie Zoologique. Chez Dentu."},{"key":"e_1_3_2_1_19_1","unstructured":"T. A. Mann H. Penedones and T. Hester. 2016. Adaptive \u03bb Least-Squares Temporal Difference Learning. arXiv:1612.09465 {cs.LG} (2016)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045594"},{"key":"e_1_3_2_1_21_1","volume-title":"Human-level control through deep reinforcement learning. Nature 518, 7540","author":"Mnih Volodymyr","year":"2015","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, and Demis Hassabis. 2015. Human-level control through deep reinforcement learning. Nature 518, 7540 (2015), 529--533."},{"key":"e_1_3_2_1_22_1","volume-title":"Vedavyas Panneershelvam, Mustafa Suleyman, Charles Beattie, Stig Petersen, Shane Legg, Volodymyr Mnih, Koray Kavukcuoglu, and David Silver.","author":"Nair Arun","year":"2015","unstructured":"Arun Nair, Praveen Srinivasan, Sam Blackwell, Cagdas Alcicek, Rory Fearon, Alessandro De Maria, Vedavyas Panneershelvam, Mustafa Suleyman, Charles Beattie, Stig Petersen, Shane Legg, Volodymyr Mnih, Koray Kavukcuoglu, and David Silver. 2015. Massively Parallel Methods for Deep Reinforcement Learning. arXiv:1507.04296 {cs.LG} (2015)."},{"key":"e_1_3_2_1_23_1","unstructured":"G. A. Rummery and M. Niranjan. 1994. On-line Q-learning using connectionist systems. Technical Report CUED\/F-INFENG\/TR 166. Cambridge University Engineering Department."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(02)00228-9"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999325.2999464"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045349"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157560"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022633531479"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/1867135.1867162"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/2998828.2998974"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/551283"},{"key":"e_1_3_2_1_32_1","volume-title":"ICML 2010 workshop on machine learning and games.","author":"Szita I.","unstructured":"I. Szita and C. Szepesv\u00e1ri. 2010. SZ-Tetris as a benchmark for studying key problems of reinforcement learning. In ICML 2010 workshop on machine learning and games."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1428.003.0041"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016191"},{"key":"e_1_3_2_1_35_1","volume-title":"Attention is all you need. arXiv:1706.03762 {cs.CL}","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. arXiv:1706.03762 {cs.CL} (2017)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157448"}],"event":{"name":"GECCO '18: Genetic and Evolutionary Computation Conference","location":"Kyoto Japan","acronym":"GECCO '18","sponsor":["SIGEVO ACM Special Interest Group on Genetic and Evolutionary Computation"]},"container-title":["Proceedings of the Genetic and Evolutionary Computation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3205455.3205486","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3205455.3205486","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:08:56Z","timestamp":1750208936000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3205455.3205486"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7,2]]},"references-count":36,"alternative-id":["10.1145\/3205455.3205486","10.1145\/3205455"],"URL":"https:\/\/doi.org\/10.1145\/3205455.3205486","relation":{},"subject":[],"published":{"date-parts":[[2018,7,2]]},"assertion":[{"value":"2018-07-02","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}